© 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. 7-RES-JB
    11. 22908
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Hard"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Hard" and its variations including references to difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uality
    -0.81
    umbn
    -0.77
    ĸļ
    -0.76
    uating
    -0.71
    idated
    -0.70
     Mens
    -0.70
    ENTS
    -0.69
    entric
    -0.67
    uated
    -0.66
    uations
    -0.65
    POSITIVE LOGITS
    ened
    1.10
    ening
    1.05
    ness
    0.97
    ball
    0.92
    coded
    0.90
    dri
    0.88
    core
    0.87
    wired
    0.87
    disk
    0.84
    cover
    0.83
    Activations Density 0.031%

    No Known Activations