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. 8-RES-JB
    6. 18867
    Prev
    Next
    INDEX
    Explanations

    terms related to raw materials or resources

    oai_token-act-pair · gpt-3.5-turbo

    the term "raw" used in various contexts

    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
    agements
    -0.84
    etheless
    -0.80
    itism
    -0.79
    agall
    -0.75
    eanor
    -0.74
    uyomi
    -0.70
    relation
    -0.70
    ŃĶ
    -0.68
    conservancy
    -0.67
    ommel
    -0.67
    POSITIVE LOGITS
    hide
    1.45
    lings
    1.23
    ls
    1.17
    lins
    1.10
     sewage
    1.07
    esome
    0.99
     materials
    0.94
    kus
    0.86
    ted
    0.84
    blood
    0.78
    Activations Density 0.015%

    No Known Activations