© 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. 4588
    Prev
    Next
    INDEX
    Explanations

    numerical values formatted as amounts or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and metrics

    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
     reconc
    -0.64
     Grac
    -0.64
     IPM
    -0.63
     seiz
    -0.62
     rob
    -0.61
     Guan
    -0.61
     aph
    -0.61
     Zen
    -0.61
     merit
    -0.61
     comprom
    -0.59
    POSITIVE LOGITS
    rued
    0.74
    ettes
    0.65
     Isles
    0.64
    umber
    0.63
    ÙĨ
    0.61
    imb
    0.60
    row
    0.58
    Runtime
    0.57
    vernment
    0.57
    icularly
    0.56
    Activations Density 0.189%

    No Known Activations