© 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. 7-RES-JB
    11. 2719
    Prev
    Next
    INDEX
    Explanations

    emotions or physical states

    oai_token-act-pair · gpt-3.5-turbo

    emotional states or characteristics of individuals in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},
    -0.73
    },{"
    -0.71
    iggurat
    -0.69
    ebin
    -0.66
     Gregg
    -0.66
    affle
    -0.65
    earch
    -0.65
    Trend
    -0.64
    "}],"
    -0.63
    equality
    -0.63
    POSITIVE LOGITS
     poised
    0.86
     burd
    0.85
     anticipating
    0.82
     forgotten
    0.81
     skipping
    0.80
     intending
    0.79
     forgetting
    0.78
     retreating
    0.73
     eager
    0.72
     shy
    0.72
    Activations Density 0.357%

    No Known Activations