© 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. 9-RES-JB
    11. 15349
    Prev
    Next
    INDEX
    Explanations

    references or mentions to specific terms or concepts in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "reference" in various contexts

    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
    keye
    -0.71
    otos
    -0.69
    ierra
    -0.68
     Cree
    -0.67
    ihad
    -0.66
    ilus
    -0.64
    oly
    -0.63
    icipated
    -0.63
    DAQ
    -0.63
    sylv
    -0.62
    POSITIVE LOGITS
    ibly
    0.76
    ENCE
    0.75
     thereto
    0.75
    ENC
    0.74
    minist
    0.73
     counting
    0.72
    cards
    0.72
    reference
    0.69
    ogue
    0.68
    PsyNetMessage
    0.67
    Activations Density 0.040%

    No Known Activations