© 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. 9-RES-JB
    11. 17954
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or awareness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of awareness and familiarity with information

    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
    oreal
    -0.72
    cific
    -0.68
    vati
    -0.67
    ospel
    -0.67
    eca
    -0.61
    emale
    -0.61
    iar
    -0.60
    rontal
    -0.60
    inals
    -0.60
    igham
    -0.60
    POSITIVE LOGITS
    tale
    0.81
     tales
    0.66
    ances
    0.65
     me
    0.63
    ANCE
    0.62
     yourselves
    0.62
    mentioned
    0.59
    INGTON
    0.57
     how
    0.57
     why
    0.56
    Activations Density 0.214%

    No Known Activations