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. 21565
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent people, organizations, and places

    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
    mble
    -0.57
    ãĥł
    -0.48
    zsche
    -0.47
    ularity
    -0.47
    LESS
    -0.46
    Discussion
    -0.46
     CLSID
    -0.46
    ãĥĨ
    -0.44
    ebook
    -0.44
    代
    -0.43
    POSITIVE LOGITS
    's
    0.46
    bugs
    0.40
     Haram
    0.40
     illegally
    0.39
    Leaks
    0.39
     Heights
    0.39
     detainees
    0.39
    ÃŃs
    0.38
     tonight
    0.38
     Fallon
    0.38
    Activations Density 1.070%

    No Known Activations