Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 9585
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or government issues

    oai_token-act-pair · gpt-3.5-turbo

    word repetitions and the use of conjunctions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uously
    -0.82
     HDL
    -0.80
    icity
    -0.76
    ious
    -0.71
    ADRA
    -0.70
    utenberg
    -0.69
    ESE
    -0.68
    Asset
    -0.67
     unfocusedRange
    -0.65
    ively
    -0.65
    POSITIVE LOGITS
     Leban
    0.65
    uddin
    0.64
    shapeshifter
    0.63
    bern
    0.63
    Fax
    0.61
    execute
    0.61
    ocked
    0.60
    Lenin
    0.59
     cones
    0.59
    fecture
    0.58
    Activations Density 0.444%

    No Known Activations