© 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. 2-RES-JB
    11. 20668
    Prev
    Next
    INDEX
    Explanations

    the names of baseball players

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĵĺ
    -0.72
    aii
    -0.70
     Nets
    -0.70
    ĨĴ
    -0.68
    estern
    -0.66
    orate
    -0.66
    izons
    -0.65
    rote
    -0.65
    uitous
    -0.64
     appl
    -0.64
    POSITIVE LOGITS
    arget
    0.76
     Ambro
    0.76
    pling
    0.70
    zza
    0.68
    $$$$
    0.67
     Stanton
    0.66
     Fitzgerald
    0.65
    DM
    0.64
     Glas
    0.62
    ctr
    0.61
    Activations Density 0.026%

    No Known Activations