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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 97
    Prev
    Next
    INDEX
    Explanations

    conditional statements indicating a specific action to be taken or considered

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Should" indicating suggestions or recommendations

    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
    herer
    -0.71
    stood
    -0.71
    natureconservancy
    -0.67
     sclerosis
    -0.63
     Puzzle
    -0.61
    CI
    -0.58
     Purpose
    -0.58
     CODE
    -0.57
    ãĥ¬
    -0.57
     maze
    -0.56
    POSITIVE LOGITS
    ering
    1.14
    ered
    1.10
    n
    0.96
     be
    0.93
    acus
    0.79
    erc
    0.78
    nt
    0.78
    uel
    0.77
    erers
    0.77
    fters
    0.76
    Activations Density 0.027%

    No Known Activations