© 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. 474
    Prev
    Next
    INDEX
    Explanations

    phrases indicating additional details or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the expression "not to mention."

    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
    hard
    -0.77
    itton
    -0.70
    arij
    -0.70
    twitch
    -0.69
    psons
    -0.66
    sis
    -0.66
    arat
    -0.65
    heres
    -0.65
    forums
    -0.63
    irm
    -0.63
    POSITIVE LOGITS
     mentioning
    0.84
    lihood
    0.80
    minus
    0.78
     nor
    0.76
     aloud
    0.72
     mention
    0.70
    _>
    0.68
     anymore
    0.68
     suffice
    0.66
     whatsoever
    0.66
    Activations Density 0.021%

    No Known Activations