© 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. 1-RES-JB
    11. 9420
    Prev
    Next
    INDEX
    Explanations

    phrases related to importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    words related to the importance or significance of events, actions, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resp
    -0.71
     Balanced
    -0.67
     Bull
    -0.66
    cker
    -0.66
    uv
    -0.64
    ergy
    -0.63
    hma
    -0.61
    Jet
    -0.61
    IDES
    -0.61
    Rail
    -0.60
    POSITIVE LOGITS
     significance
    1.33
     importance
    1.05
    notation
    0.93
    uality
    0.93
     relevance
    0.92
    notations
    0.92
     implications
    0.86
    xual
    0.84
     proble
    0.84
    atility
    0.81
    Activations Density 0.005%

    No Known Activations