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. 5-RES-JB
    6. 647
    Prev
    Next
    INDEX
    Explanations

    action verbs related to changing, fixing, or transforming things

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with actions or processes of change and improvement

    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
    dt
    -0.60
    si
    -0.60
    see
    -0.59
    so
    -0.58
    behind
    -0.58
    debian
    -0.56
    tar
    -0.56
    talk
    -0.55
    eria
    -0.55
    ère
    -0.54
    POSITIVE LOGITS
    redients
    0.89
     oneself
    0.80
    BuyableInstoreAndOnline
    0.71
    ADRA
    0.64
    HAM
    0.59
     INTO
    0.58
    issance
    0.57
    ãĥ¼ãĥĨ
    0.55
     constituents
    0.55
    olphin
    0.55
    Activations Density 0.491%

    No Known Activations