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. 18291
    Prev
    Next
    INDEX
    Explanations

    instances of the word "knock" followed by a preposition or possessive pronoun, specifically focusing on actions related to doors

    oai_token-act-pair · gpt-3.5-turbo

    references to knocking on doors

    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
    ILLE
    -0.73
    pard
    -0.69
    UAL
    -0.68
    utan
    -0.67
    ENN
    -0.66
    ngth
    -0.64
    abama
    -0.64
    APH
    -0.64
     Disaster
    -0.62
    oleon
    -0.62
    POSITIVE LOGITS
     doors
    1.14
     door
    0.94
     wood
    0.86
     gates
    0.85
     walls
    0.79
    door
    0.76
     throats
    0.76
     bushes
    0.74
    ongyang
    0.73
    houses
    0.73
    Activations Density 0.121%

    No Known Activations