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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 4486
    Prev
    Next
    INDEX
    Explanations

    mentions related to the talk show host Jimmy Kimmel

    oai_token-act-pair · gpt-3.5-turbo

    references to television hosts and their shows

    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
    export
    -0.67
     formation
    -0.65
    ogun
    -0.64
    rongh
    -0.64
    akings
    -0.63
     bonds
    -0.62
     crest
    -0.61
    zh
    -0.61
    activation
    -0.60
     deed
    -0.60
    POSITIVE LOGITS
     Tonight
    1.18
     Hannity
    1.18
     aired
    1.12
     interviewer
    1.07
    gyn
    1.06
     airing
    1.05
    CNN
    0.99
     Interview
    0.98
     broadcasts
    0.97
    NBC
    0.95
    Activations Density 0.175%

    No Known Activations