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. 11740
    Prev
    Next
    INDEX
    Explanations

    the word "all" followed by a hyphen and a descriptive adjective or noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "all" and contextually related concepts

    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
    EStream
    -0.84
     KH
    -0.73
    hyde
    -0.69
     Challenges
    -0.68
     Puzzles
    -0.65
    ulty
    -0.65
    TeX
    -0.64
    ongyang
    -0.64
    awaru
    -0.64
     Janeiro
    -0.64
    POSITIVE LOGITS
    âĢij
    0.79
    -
    0.77
    auc
    0.77
    adic
    0.76
    usive
    0.74
    tackle
    0.71
    xious
    0.71
    ailable
    0.69
    ocratic
    0.68
    ctic
    0.68
    Activations Density 0.048%

    No Known Activations