© 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. 0-RES-JB
    6. 2735
    Prev
    Next
    INDEX
    Explanations

    phrases related to atheism and related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to atheism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stash
    -0.81
    externalActionCode
    -0.80
    ucc
    -0.79
     superpower
    -0.73
     KGB
    -0.71
     nonexistent
    -0.69
     sphere
    -0.68
    etime
    -0.67
     shine
    -0.66
    azo
    -0.66
    POSITIVE LOGITS
     Athe
    3.56
     Arg
    1.32
    tons
    1.27
     Hep
    1.24
     Aad
    1.10
     Frie
    1.08
     Eur
    1.02
     Noct
    1.01
     Brid
    0.98
     Guth
    0.95
    Activations Density 0.050%

    No Known Activations