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. 7-RES-JB
    6. 1072
    Prev
    Next
    INDEX
    Explanations

    instances of people coming forward with information or accusations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "come forward."

    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
    tein
    -0.70
    Rocket
    -0.67
    rip
    -0.66
    OME
    -0.60
     Goo
    -0.60
    @@@@@@@@
    -0.59
     Sent
    -0.58
     Cong
    -0.58
     Fare
    -0.57
    knife
    -0.57
    POSITIVE LOGITS
     voluntarily
    0.90
    onyms
    0.80
     anonymously
    0.73
     allegations
    0.71
     withd
    0.71
     testimonies
    0.67
     willingly
    0.67
     alleging
    0.66
    imately
    0.66
     publicly
    0.65
    Activations Density 0.023%

    No Known Activations