© 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. 19585
    Prev
    Next
    INDEX
    Explanations

    characters from a non-English alphabet

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols in the text

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    omorphic
    -0.59
     developing
    -0.38
     cryptocurrency
    -0.37
     sadd
    -0.37
    kus
    -0.37
    alore
    -0.37
    ãĥ£
    -0.37
     growing
    -0.36
    lihood
    -0.36
    POSITIVE LOGITS
    Dialogue
    0.52
    ixie
    0.51
    Winged
    0.49
     Ibid
    0.46
    ONSORED
    0.45
    ucket
    0.45
    ł
    0.45
    endif
    0.45
     SolidGoldMagikarp
    0.44
     Execution
    0.43
    Activations Density 0.819%

    No Known Activations