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. 4-RES-JB
    6. 3895
    Prev
    Next
    INDEX
    Explanations

    locations or presence of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word "around" in various contexts related to presence or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qua
    -0.71
     Dalai
    -0.65
    isy
    -0.62
     gard
    -0.61
    HO
    -0.59
     chord
    -0.58
     Tigers
    -0.58
    uras
    -0.58
     Guilty
    -0.58
    BT
    -0.57
    POSITIVE LOGITS
    abouts
    0.93
     corners
    0.83
    lihood
    0.77
     ..........
    0.71
    anism
    0.70
    essage
    0.69
    nces
    0.68
    irlfriend
    0.68
    atform
    0.68
    rocal
    0.68
    Activations Density 0.044%

    No Known Activations