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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 520
    Prev
    Next
    INDEX
    Explanations

    phrases related to rejecting, getting rid of, or discarding something

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of "throwing out" or discarding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APH
    -0.80
    ÃŁ
    -0.77
    ND
    -0.76
    CLA
    -0.73
    SET
    -0.71
    Marginal
    -0.69
    going
    -0.68
    achine
    -0.68
     Wem
    -0.67
    Ë
    -0.67
    POSITIVE LOGITS
     overboard
    0.91
     tant
    0.80
     insult
    0.71
     blame
    0.70
     grenades
    0.68
     Tuls
    0.67
    poon
    0.62
     Shal
    0.62
    rav
    0.62
     grenade
    0.62
    Activations Density 0.110%

    No Known Activations