© 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. 1-RES-JB
    11. 24215
    Prev
    Next
    INDEX
    Explanations

    terms related to physical discs or media storage

    oai_token-act-pair · gpt-3.5-turbo

    references to specific disc or DVD releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.73
    mberg
    -0.71
    ĸļ
    -0.70
    aukee
    -0.67
    xual
    -0.66
    cki
    -0.66
    Ń·
    -0.64
     deed
    -0.63
    ked
    -0.63
    atory
    -0.61
    POSITIVE LOGITS
    ussions
    1.21
     Disc
    1.07
    ourses
    1.03
    washer
    0.99
    ourse
    0.98
    ontent
    0.97
    ont
    0.92
    rim
    0.91
    rep
    0.87
    overed
    0.85
    Activations Density 0.008%

    No Known Activations