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. 4-RES-JB
    6. 3580
    Prev
    Next
    INDEX
    Explanations

    phrases or descriptions emphasizing excellence or high quality

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "impressive."

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

    No Comments

    Negative Logits
    ©¶æ
    -0.83
    sole
    -0.76
    ajor
    -0.74
    iche
    -0.72
    opter
    -0.69
    uter
    -0.68
    few
    -0.67
    pher
    -0.67
    nav
    -0.67
    rigan
    -0.66
    POSITIVE LOGITS
     feats
    1.06
     feat
    0.99
     accomplishment
    0.93
     accomplishments
    0.86
    issance
    0.82
     achievement
    0.80
     enough
    0.78
     accol
    0.78
     impressive
    0.77
    ments
    0.77
    Activations Density 0.014%

    No Known Activations