© 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. 4414
    Prev
    Next
    INDEX
    Explanations

    references to different concepts of gods or deities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "god."

    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
     Carb
    -0.74
     Hyde
    -0.71
    DonaldTrump
    -0.69
     Lans
    -0.68
     Diabetes
    -0.67
     Retirement
    -0.67
     McGr
    -0.66
     Peninsula
    -0.66
    EStreamFrame
    -0.65
    phrine
    -0.65
    POSITIVE LOGITS
    mother
    1.25
    father
    1.23
    parents
    1.13
    frey
    1.08
    liness
    0.99
    zilla
    0.92
    esses
    0.88
    sword
    0.87
     damn
    0.86
    amn
    0.86
    Activations Density 0.008%

    No Known Activations