© 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. 7596
    Prev
    Next
    INDEX
    Explanations

    instances of words being replaced with other words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating replacement or substitution

    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
    icious
    -0.91
    imentary
    -0.72
    enture
    -0.70
    antage
    -0.70
    emetery
    -0.67
    LIB
    -0.65
    Streamer
    -0.64
    PLIED
    -0.63
     exceeded
    -0.61
    zai
    -0.61
    POSITIVE LOGITS
     permanent
    0.67
    livion
    0.67
     normal
    0.66
     obsolete
    0.66
     Sonny
    0.65
    rities
    0.65
    ;}
    0.64
     lifeless
    0.63
    emort
    0.63
     nonexistent
    0.63
    Activations Density 0.245%

    No Known Activations