© 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. 3-RES-JB
    11. 1761
    Prev
    Next
    INDEX
    Explanations

    the mention of specific terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific terms or terminologies in a discussion

    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
    âĹ¼
    -0.75
    NetMessage
    -0.71
    ramid
    -0.69
     choir
    -0.68
    psey
    -0.67
    ECTION
    -0.66
    hs
    -0.66
     Guerrero
    -0.66
    DERR
    -0.66
     Flavoring
    -0.65
    POSITIVE LOGITS
    marks
    0.98
    icide
    0.88
    sworth
    0.86
    mark
    0.84
    marked
    0.83
    camp
    0.78
    icides
    0.78
    uncle
    0.76
    term
    0.76
    ifier
    0.73
    Activations Density 0.022%

    No Known Activations