© 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. 21323
    Prev
    Next
    INDEX
    Explanations

    words related to describing or discussing personality traits and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "character" in various contexts, often relating to traits or characteristics of individuals, narratives, or entities

    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
    yg
    -0.78
    EMS
    -0.68
    IDA
    -0.67
    VEN
    -0.64
    hner
    -0.63
    VERTIS
    -0.62
    nesday
    -0.62
    riel
    -0.62
    xon
    -0.61
    liga
    -0.61
    POSITIVE LOGITS
    istically
    1.54
    istics
    1.51
    izations
    1.34
    izes
    1.20
    isations
    1.05
     assassination
    1.04
    isation
    1.01
    izing
    0.98
    ised
    0.97
     traits
    0.93
    Activations Density 0.031%

    No Known Activations