© 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. 7-RES-JB
    11. 17139
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals and organizations

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" indicating a list of entities or individuals involved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BIP
    -0.83
    blocks
    -0.76
    mop
    -0.76
    Applications
    -0.75
    POST
    -0.73
    etary
    -0.72
    physical
    -0.70
    imil
    -0.70
    ĻĤ
    -0.70
    open
    -0.69
    POSITIVE LOGITS
     others
    1.04
     colleagues
    1.01
     assorted
    0.97
     colleague
    0.88
     fellow
    0.88
     his
    0.79
     associates
    0.79
     other
    0.76
     collaborator
    0.76
     vice
    0.75
    Activations Density 0.218%

    No Known Activations