© 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. 8571
    Prev
    Next
    INDEX
    Explanations

    words related to storytelling and community events

    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
    61
    +0.14
    0.8%
    122
    +0.14
    0.7%
    47
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.14
    0.03
    1575
    +0.14
    0.03
    896
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.07
    Datuak
    -0.56
     îna
    -0.54
     uș
    -0.54
     Lombardo
    -0.54
     quitted
    -0.54
     Gonzalez
    -0.53
     McQu
    -0.52
     eventdata
    -0.52
     blest
    -0.51
    POSITIVE LOGITS
     Bea
    1.38
    Bea
    1.36
     Beam
    1.25
    Beam
    1.17
     beam
    1.16
     beams
    1.14
     bea
    1.12
    beam
    1.12
     BEAM
    1.12
     Beams
    1.09
    Activations Density 0.422%

    No Known Activations