© 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. 8-RES-JB
    11. 812
    Prev
    Next
    INDEX
    Explanations

    words related to negative characteristics or behaviors such as selfishness, ignorance, or insensitivity

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and nouns that describe negative traits or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emis
    -0.83
    ovember
    -0.83
    ioxide
    -0.82
     GOODMAN
    -0.78
    URA
    -0.77
    è£ħ
    -0.76
    orthy
    -0.75
    oother
    -0.75
    lished
    -0.74
    available
    -0.73
    POSITIVE LOGITS
     tendencies
    1.11
     arrogance
    1.06
    ness
    1.06
     antics
    1.01
     behaviour
    1.00
     behavior
    0.98
     stupidity
    0.97
     zeal
    0.97
     greed
    0.95
     impulses
    0.94
    Activations Density 0.190%

    No Known Activations