© 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. 11-RES-JB
    11. 15742
    Prev
    Next
    INDEX
    Explanations

    references to supernatural entities, particularly the devil

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of the devil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.71
    here
    -0.69
    raltar
    -0.68
    RFC
    -0.63
     Kislyak
    -0.62
     adequ
    -0.62
    CI
    -0.62
     easing
    -0.62
    bered
    -0.62
    Avg
    -0.61
    POSITIVE LOGITS
    ishly
    1.22
     incarn
    1.06
     worsh
    1.03
    ish
    0.91
     Fruit
    0.84
     Slayer
    0.83
     Summoner
    0.82
    stration
    0.82
     Rays
    0.81
    iac
    0.80
    Activations Density 0.064%

    No Known Activations