© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 14400
    Prev
    Next
    INDEX
    Explanations

    terms related to 'bi-' prefixes, with a stronger emphasis on those with a value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "bi" related terms, indicating a focus on biotechnology and biographical subjects

    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
    lain
    -0.88
    swick
    -0.69
    inho
    -0.68
     Rapids
    -0.65
     sink
    -0.65
     Nept
    -0.64
    MENTS
    -0.64
     Rack
    -0.63
     Chero
    -0.62
     Bride
    -0.62
    POSITIVE LOGITS
    ochem
    1.42
    otechnology
    1.32
    weekly
    1.28
    ochemistry
    1.28
    ographies
    1.27
    omed
    1.23
    ographical
    1.23
    ocide
    1.21
    omes
    1.20
    odynamic
    1.17
    Activations Density 0.028%

    No Known Activations