© 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. 15227
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to significant size or importance

    oai_token-act-pair · gpt-3.5-turbo

    the word "huge" and its variations related to size or impact

    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
    Reviewed
    -0.84
    ices
    -0.84
    tein
    -0.78
    cling
    -0.77
    ople
    -0.76
    utics
    -0.75
    gemony
    -0.74
    robe
    -0.73
    istry
    -0.73
    former
    -0.71
    POSITIVE LOGITS
     amounts
    1.13
     amount
    0.95
     earthqu
    0.95
     disproportion
    0.93
     chunks
    0.92
     quantities
    0.91
     chunk
    0.90
     disparity
    0.86
     difference
    0.86
     leaps
    0.84
    Activations Density 0.036%

    No Known Activations