© 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. 9-RES-JB
    11. 10107
    Prev
    Next
    INDEX
    Explanations

    words related to qualities or conditions that have a strong impact or significance

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe various qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenant
    -0.94
    vere
    -0.83
    CLAIM
    -0.81
    elected
    -0.79
    ©¶æ
    -0.75
    OIL
    -0.75
    famous
    -0.72
    cised
    -0.71
     Canaver
    -0.71
    ador
    -0.71
    POSITIVE LOGITS
    ness
    0.98
     ecosystem
    0.92
    ities
    0.92
     ones
    0.91
     environment
    0.88
     landscape
    0.88
     aspects
    0.86
     outcome
    0.86
     structures
    0.85
     capabilities
    0.84
    Activations Density 0.399%

    No Known Activations