Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21762
    Prev
    Next
    INDEX
    Explanations

    words related to decisions or choices

    oai_token-act-pair · gpt-3.5-turbo

    words related to decision-making or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inav
    -0.76
    psc
    -0.69
    orah
    -0.68
     gobl
    -0.68
    ĻĤ
    -0.68
     downtime
    -0.63
     Logged
    -0.61
    aptic
    -0.61
    accompan
    -0.61
    obin
    -0.60
    POSITIVE LOGITS
    naire
    1.14
    eers
    1.14
    eering
    1.12
    eer
    1.10
    ition
    1.06
    ary
    1.00
    itious
    0.98
    ally
    0.97
    itions
    0.93
    ality
    0.91
    Activations Density 0.034%

    No Known Activations