© 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. 0-RES-JB
    11. 1855
    Prev
    Next
    INDEX
    Explanations

    fashion-related items, particularly those made of leather

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    486
    +0.11
    0.4%
    680
    +0.09
    0.3%
    228
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1268
    +0.11
    0.03
    486
    +0.09
    0.02
    1130
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.13
    AddColumn
    -0.68
    żdy
    -0.66
    toContain
    -0.60
     "..\..\..\
    -0.58
    })();
    -0.57
    ComponentModel
    -0.56
    zydent
    -0.56
    toHaveBeenCalled
    -0.55
    CreateIndex
    -0.54
    POSITIVE LOGITS
     leather
    2.44
     Leather
    2.36
    Leather
    2.31
    leather
    2.26
     cuir
    1.44
     Luglio
    1.24
     Ottobre
    1.22
     maroc
    1.19
     Settembre
    1.11
     Giugno
    1.10
    Activations Density 0.194%

    No Known Activations