© 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. 4-RES-JB
    11. 10894
    Prev
    Next
    INDEX
    Explanations

    references to military ranks or titles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "General."

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

    No Comments

    Negative Logits
    ï¸
    -0.87
    bley
    -0.83
    SourceFile
    -0.78
    pher
    -0.75
    lot
    -0.74
    nob
    -0.73
    rb
    -0.70
    ÄŁ
    -0.68
     Frie
    -0.68
    COMPLE
    -0.67
    POSITIVE LOGITS
    izations
    1.04
     Electric
    0.90
    ization
    0.88
     Dynamics
    0.84
    isations
    0.84
    ize
    0.76
    isation
    0.75
    izing
    0.74
    ihilation
    0.74
    ized
    0.73
    Activations Density 0.021%

    No Known Activations