© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 17418
    Prev
    Next
    INDEX
    Explanations

    phrases related to lack of communication or suppression

    oai_token-act-pair · gpt-3.5-turbo

    references to silence or its impacts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agers
    -0.72
    anooga
    -0.70
    amins
    -0.70
    isin
    -0.67
    drivers
    -0.66
    issue
    -0.66
    rollers
    -0.65
    swick
    -0.64
    OPER
    -0.63
    omet
    -0.62
    POSITIVE LOGITS
     silence
    0.99
     Silence
    0.97
    rences
    0.92
    etooth
    0.83
    creen
    0.82
    isSpecialOrderable
    0.76
     cooker
    0.74
    gren
    0.72
    eless
    0.71
    ences
    0.70
    Activations Density 0.010%

    No Known Activations