Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22882
    Prev
    Next
    INDEX
    Explanations

    technical terms and industry-specific language

    oai_token-act-pair · gpt-3.5-turbo

    specific financial and economic terms or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.83
    anka
    -0.78
    omore
    -0.76
    etsk
    -0.76
    tons
    -0.74
    unci
    -0.73
    aminer
    -0.73
    olulu
    -0.73
    lahoma
    -0.72
    acity
    -0.72
    POSITIVE LOGITS
    LIN
    1.75
    ING
    1.69
    ER
    1.67
    IES
    1.66
    OFF
    1.64
    NING
    1.64
    WOR
    1.63
    NER
    1.62
    LES
    1.61
    TER
    1.59
    Activations Density 0.223%

    No Known Activations