© 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. 4-RES-JB
    11. 15301
    Prev
    Next
    INDEX
    Explanations

    phrases that involve calling or labeling something

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to self-identification

    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
    ersen
    -0.69
    iland
    -0.61
    ockets
    -0.59
    aten
    -0.59
     cough
    -0.58
    midt
    -0.57
     volcano
    -0.57
    ----------------
    -0.57
    edia
    -0.57
     Tribune
    -0.56
    POSITIVE LOGITS
     "#
    0.86
    selves
    0.70
     ''
    0.69
     '
    0.68
     ``
    0.68
    named
    0.67
    runners
    0.66
    geant
    0.63
    leaders
    0.63
     slogans
    0.63
    Activations Density 0.194%

    No Known Activations