© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7313
    Prev
    Next
    INDEX
    Explanations

    specifically the characters "]" and words that follow them

    oai_token-act-pair · gpt-3.5-turbo

    references to quotations or citations

    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
    ĸļ
    -0.90
    ĪĴ
    -0.83
    Ń·
    -0.76
    İĭ
    -0.75
    ©¶æ¥µ
    -0.69
    anium
    -0.68
    ãĥł
    -0.64
    ãĤ©
    -0.63
    elsh
    -0.62
    ĻĤ
    -0.62
    POSITIVE LOGITS
    },"
    0.76
    Nin
    0.68
    ...]
    0.67
    appropriate
    0.65
    >:
    0.65
    selves
    0.65
    >]
    0.63
    indust
    0.61
    conom
    0.60
    âĨ
    0.60
    Activations Density 0.050%

    No Known Activations