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. 2-RES-JB
    6. 37
    Prev
    Next
    INDEX
    Explanations

    references to sacral or sacrificial themes

    oai_token-act-pair · gpt-3.5-turbo

    references to sacrificial elements or acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words beginning with "sac"

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.82
     Cheong
    -0.78
    DERR
    -0.74
     Kessler
    -0.70
    ãĥī
    -0.69
     Roosevelt
    -0.67
     Clarkson
    -0.67
    agher
    -0.66
     Hungry
    -0.65
     Turk
    -0.65
    POSITIVE LOGITS
    ificial
    1.17
    rament
    1.14
    char
    1.07
    ram
    1.01
    rifice
    1.01
    het
    0.96
    anus
    0.96
     sac
    0.95
    ree
    0.93
    ré
    0.93
    Activations Density 0.008%

    No Known Activations