© 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. 10-RES-JB
    11. 14091
    Prev
    Next
    INDEX
    Explanations

    references to positions or descriptions of individuals in photographs

    oai_token-act-pair · gpt-3.5-turbo

    closing parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.56
    ãĥ¥
    -0.56
    ((
    -0.55
    Ļ½
    -0.54
    humane
    -0.53
     eg
    -0.52
     unequal
    -0.52
    %%%%
    -0.51
    cdn
    -0.51
     deterrence
    -0.51
    POSITIVE LOGITS
    hatt
    0.65
     pione
    0.63
    oÄŁ
    0.62
     ,
    0.61
    ortium
    0.60
    acca
    0.60
     eyed
    0.60
    aughs
    0.59
     wrote
    0.59
    /"
    0.58
    Activations Density 0.119%

    No Known Activations