© 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. 13226
    Prev
    Next
    INDEX
    Explanations

    references to a particular organization or company with the acronym "AS"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the acronym "AS" followed by its numerical identifiers

    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
    ãĥķãĤ©
    -0.92
    sburgh
    -0.78
    ãĤª
    -0.76
    ãĤ£
    -0.75
    Ö¼
    -0.73
    Synopsis
    -0.71
    д
    -0.68
    toggle
    -0.68
    ãĤ¸
    -0.66
    Released
    -0.64
    POSITIVE LOGITS
    BC
    0.90
    X
    0.81
    SP
    0.78
    FP
    0.77
    MIN
    0.77
    isons
    0.77
    RS
    0.75
    IZ
    0.74
    emic
    0.72
    SI
    0.72
    Activations Density 0.020%

    No Known Activations