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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5137
    Prev
    Next
    INDEX
    Explanations

    phrases denoting emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to abstract concepts or ideas, particularly those expressed with the character 'âĢĶ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commun
    -0.78
    perate
    -0.76
    ieth
    -0.74
    worms
    -0.73
    ordinate
    -0.71
    erald
    -0.68
    uder
    -0.67
    uminati
    -0.67
    reens
    -0.67
    illance
    -0.67
    POSITIVE LOGITS
    ————————
    1.69
    ————
    1.63
    ————————————————
    1.35
    ——
    0.93
    _-
    0.90
    particularly
    0.80
    especially
    0.78
    âĢķ
    0.76
    perhaps
    0.76
    ––
    0.75
    Activations Density 0.127%

    No Known Activations