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. 16516
    Prev
    Next
    INDEX
    Explanations

    mentions of actions related to authority or exclusive rights

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "rog" 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
    birth
    -0.70
    aved
    -0.68
     goodbye
    -0.65
     Fas
    -0.64
    ICAN
    -0.57
    rix
    -0.57
     Machina
    -0.56
    INESS
    -0.56
    sever
    -0.56
    fig
    -0.55
    POSITIVE LOGITS
    raphic
    1.32
    raphics
    1.22
    raph
    1.20
    allery
    1.07
    roup
    1.06
    aming
    0.99
    rams
    0.95
    atory
    0.95
    roups
    0.93
    ues
    0.92
    Activations Density 0.045%

    No Known Activations