© 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. 10-RES-JB
    11. 11090
    Prev
    Next
    INDEX
    Explanations

    words related to the characteristics and behaviors of people

    oai_token-act-pair · gpt-3.5-turbo

    statements about human traits or behaviors and their tendencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osate
    -0.81
    ospons
    -0.80
    bernatorial
    -0.75
     Anniversary
    -0.75
    andise
    -0.73
    ornia
    -0.71
     legality
    -0.70
    inia
    -0.69
    reau
    -0.67
    tains
    -0.66
    POSITIVE LOGITS
     aware
    1.19
     incapable
    1.18
     happiest
    1.18
     smarter
    1.17
     unaware
    1.15
     accustomed
    1.13
     afraid
    1.11
     happier
    1.11
     obsessed
    1.10
     willing
    1.09
    Activations Density 0.256%

    No Known Activations