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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11682
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or proper nouns, like names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that are empty or contain no activations, indicating a lack of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.76
    Ò
    -0.72
    /"
    -0.71
     elsewhere
    -0.69
     without
    -0.69
     thereby
    -0.68
    GPU
    -0.68
    —-
    -0.68
     regardless
    -0.67
     beforehand
    -0.64
    POSITIVE LOGITS
    resa
    1.38
    oret
    1.34
    odore
    1.33
    ories
    1.33
    orem
    1.29
    atre
    1.15
     Basics
    1.02
    sis
    0.99
     easiest
    0.99
    ory
    0.94
    Activations Density 0.334%

    No Known Activations