© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1212
    Prev
    Next
    INDEX
    Explanations

    locations and events related to Connecticut

    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
    1103
    +0.17
    0.9%
    1133
    +0.15
    0.8%
    241
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.17
    0.04
    1133
    +0.15
    0.03
    1103
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.34
     négociations
    -0.54
     defray
    -0.54
    <?
    -0.53
     rehabilitate
    -0.53
     endow
    -0.53
    FTFY
    -0.53
     disbur
    -0.52
     réunions
    -0.52
    Lmfao
    -0.51
    POSITIVE LOGITS
     Connecticut
    1.49
    Connecticut
    1.42
     CT
    1.30
     Hartford
    1.12
     Conn
    1.10
    CT
    1.10
    cticut
    1.04
    Hart
    0.96
     ct
    0.92
     Ct
    0.91
    Activations Density 0.402%

    No Known Activations