© 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. 23184
    Prev
    Next
    INDEX
    Explanations

    mentions of the Marvel character Hulk

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Hulk" and related terms

    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
    İĭ
    -0.89
     Continued
    -0.84
    £ı
    -0.72
     Candle
    -0.70
    cale
    -0.66
     livest
    -0.66
     Granted
    -0.64
     reproduced
    -0.63
    changes
    -0.63
     pronounced
    -0.63
    POSITIVE LOGITS
    ulk
    1.34
    ulkan
    0.89
    regate
    0.88
    owicz
    0.84
    anova
    0.81
    adin
    0.78
    rats
    0.78
    ernaut
    0.78
    buster
    0.77
    regation
    0.77
    Activations Density 0.008%

    No Known Activations