© 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. 12266
    Prev
    Next
    INDEX
    Explanations

    phrases related to documents, regulations, and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with relevance and contextual relationships in discussions

    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
    ̶
    -0.79
    another
    -0.79
    Cola
    -0.76
    Äį
    -0.74
    osate
    -0.73
    ©¶æ
    -0.73
    feat
    -0.72
    atever
    -0.72
    ÅŁ
    -0.71
     simply
    -0.71
    POSITIVE LOGITS
     portions
    0.93
     portion
    0.92
     sections
    0.90
     amount
    0.89
     paperwork
    0.87
     pieces
    0.84
     amounts
    0.82
     fields
    0.82
     chapters
    0.80
     resources
    0.79
    Activations Density 0.122%

    No Known Activations