© 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. 19462
    Prev
    Next
    INDEX
    Explanations

    technical terms and job requirements that may relate to information technology or maintenance fields

    oai_token-act-pair · gpt-3.5-turbo

    instances of detailed descriptions or specifications related to product characteristics or services

    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
    abouts
    -0.85
    hement
    -0.83
    ĸļ
    -0.79
    ername
    -0.72
    uto
    -0.69
    iatus
    -0.68
    uan
    -0.67
     intervened
    -0.63
    acers
    -0.62
    eworks
    -0.61
    POSITIVE LOGITS
    âĵĺ
    1.17
    database
    0.83
    Usage
    0.79
    SOURCE
    0.76
    VERTISEMENT
    0.73
    SIM
    0.70
    Conclusion
    0.69
     IPM
    0.67
    Availability
    0.67
    Allows
    0.66
    Activations Density 0.286%

    No Known Activations