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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6025
    Prev
    Next
    INDEX
    Explanations

    text enclosed in unusual characters (e.g. Ċ) that likely signify special formatting or symbols in the document

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to uncertainty or ambiguity in situations

    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
     endeav
    -0.77
     prelim
    -0.74
    arching
    -0.70
    etheless
    -0.69
     conscious
    -0.69
    idays
    -0.68
    bda
    -0.67
     arisen
    -0.65
     unsc
    -0.65
     messy
    -0.64
    POSITIVE LOGITS
    Wilson
    0.96
    Said
    0.93
    Mos
    0.93
    QUI
    0.91
    Trivia
    0.90
    Lev
    0.89
    Spoiler
    0.88
    Hay
    0.83
    RAW
    0.83
    Developer
    0.82
    Activations Density 0.199%

    No Known Activations