© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10128
    Prev
    Next
    INDEX
    Explanations

    phrases indicating accompaniment or presence of someone or something

    oai_token-act-pair · gpt-3.5-turbo

    words indicating accompaniment or joining in various contexts

    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
    holder
    -0.74
     balance
    -0.72
    ouf
    -0.69
    holders
    -0.64
    knife
    -0.60
     nuisance
    -0.59
    trade
    -0.58
    hang
    -0.57
     dope
    -0.55
     Combine
    -0.55
    POSITIVE LOGITS
     aback
    0.90
    ĸļ
    0.85
    anwhile
    0.78
    BY
    0.74
     by
    0.72
    by
    0.72
     accomp
    0.69
    PsyNetMessage
    0.66
    Eva
    0.65
    escription
    0.64
    Activations Density 0.111%

    No Known Activations