© 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. 8-RES-JB
    11. 4553
    Prev
    Next
    INDEX
    Explanations

    computer code snippets

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numeric values and structured data references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ranch
    -0.54
    atel
    -0.51
    ococ
    -0.46
     sovere
    -0.45
    azo
    -0.44
    ometown
    -0.43
     POLITICO
    -0.43
    attled
    -0.42
    laden
    -0.42
    irements
    -0.42
    POSITIVE LOGITS
     =================================================================
    0.74
    <|endoftext|>
    0.71
     Amen
    0.66
    APTER
    0.64
    ----------------------------------------------------------------
    0.62
    ----------
    0.62
    ****************
    0.62
     --------------------------------
    0.61
     ----------------
    0.61
     ********************************
    0.60
    Activations Density 2.640%

    No Known Activations