© 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. 10-RES-JB
    11. 12889
    Prev
    Next
    INDEX
    Explanations

    texts discussing expertise or mastery in various skills

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express knowledge or understanding of actions and skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vertisement
    -0.74
    atform
    -0.74
    bridge
    -0.74
    POST
    -0.68
    enture
    -0.66
     hereafter
    -0.64
    idon
    -0.64
    inth
    -0.63
    swick
    -0.63
    76561
    -0.62
    POSITIVE LOGITS
     lucky
    0.86
     fragile
    0.83
     much
    0.83
     to
    0.82
     important
    0.80
     difficult
    0.80
     messed
    0.79
    itzer
    0.79
     hard
    0.78
     fucked
    0.76
    Activations Density 0.051%

    No Known Activations