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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 22777
    Prev
    Next
    INDEX
    Explanations

    terms related to legal statuses or permissions, especially in the context of asylum, funding, or certification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal permissions and status, particularly asylum and funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rouse
    -0.80
     rall
    -0.66
     iceberg
    -0.60
     depress
    -0.60
    rir
    -0.60
     depths
    -0.59
    audi
    -0.57
    tra
    -0.56
    cycl
    -0.56
    icago
    -0.56
    POSITIVE LOGITS
    ocobo
    0.76
     Tradable
    0.72
    thood
    0.71
    è»
    0.67
     entit
    0.66
    DragonMagazine
    0.66
    DERR
    0.66
    PROV
    0.65
     à¤
    0.64
    ãĥĸ
    0.64
    Activations Density 0.283%

    No Known Activations