© 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. 3-RES-JB
    6. 11452
    Prev
    Next
    INDEX
    Explanations

    names, specifically the name "Gwen Owen"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĺħ
    -0.78
     Seym
    -0.76
    pmwiki
    -0.72
     mathemat
    -0.71
     practicable
    -0.71
    Ħ¢
    -0.68
     suscept
    -0.66
    osate
    -0.65
    cffff
    -0.65
     mosqu
    -0.65
    POSITIVE LOGITS
    wen
    1.22
    borough
    1.00
    burn
    0.96
    mere
    0.95
    igan
    0.87
     Kenobi
    0.87
    burgh
    0.84
    boro
    0.83
    pool
    0.83
    yk
    0.83
    Activations Density 0.009%

    No Known Activations