© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4548
    Prev
    Next
    INDEX
    Explanations

    words related to confessions or sharing personal stories, particularly those of a sensitive nature

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    197
    +0.17
    0.8%
    1363
    +0.14
    0.7%
    893
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.17
    0.04
    197
    +0.14
    0.03
    1896
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.19
    margin
    -0.60
    MigrationBuilder
    -0.59
    Cuer
    -0.59
    scalatest
    -0.58
    Technologie
    -0.57
    AutoScaleMode
    -0.57
    Välislingid
    -0.57
    पया
    -0.57
    Mã
    -0.56
    POSITIVE LOGITS
     Conf
    1.26
     Confessions
    1.22
     conf
    1.18
     confessions
    1.15
     Confession
    1.09
    Conf
    1.07
     CONF
    1.06
     confession
    1.04
     Confu
    1.03
    conf
    1.02
    Activations Density 0.316%

    No Known Activations