© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 9847
    Prev
    Next
    INDEX
    Explanations

    references to a specific name (e.g. "Yeoh")

    oai_token-act-pair · gpt-3.5-turbo

    references to voting or decision-making 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
    ctica
    -0.77
    lished
    -0.74
    hedral
    -0.74
    ITY
    -0.72
    NAT
    -0.71
    ENA
    -0.70
    ãĥ´ãĤ¡
    -0.69
    ORY
    -0.67
    phis
    -0.66
    ENTS
    -0.65
    POSITIVE LOGITS
    terday
    0.90
    ldon
    0.88
    oman
    0.87
    asing
    0.83
    eder
    0.81
    xt
    0.78
    asers
    0.76
    ats
    0.74
    asure
    0.74
    468
    0.74
    Activations Density 0.029%

    No Known Activations