© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 18459
    Prev
    Next
    INDEX
    Explanations

    words related to negative or extreme adjectives

    oai_token-act-pair · gpt-3.5-turbo

    prefixes and terms related to negative or problematic qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.72
    Reviewer
    -0.68
     Angels
    -0.63
     Blacks
    -0.63
    stones
    -0.59
    tops
    -0.58
     ecstasy
    -0.58
     Jackets
    -0.58
     ashes
    -0.57
     Balls
    -0.56
    POSITIVE LOGITS
    cedented
    0.99
    achable
    0.81
    ivable
    0.81
    itable
    0.79
    iable
    0.78
    izable
    0.78
    isable
    0.77
    vised
    0.75
    ended
    0.75
    icable
    0.73
    Activations Density 0.101%

    No Known Activations