© 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. 11-RES-JB
    11. 18751
    Prev
    Next
    INDEX
    Explanations

    verbiage related to copyright permissions and terms of use

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the copyright and distribution of creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vets
    -0.70
    laughs
    -0.66
     Vet
    -0.63
    worth
    -0.61
     Voting
    -0.59
     Amber
    -0.58
    mber
    -0.58
    chel
    -0.56
    Case
    -0.56
    ecycle
    -0.55
    POSITIVE LOGITS
     Attribution
    0.82
     derivative
    0.82
     reproduction
    0.78
     redistributed
    0.76
     remix
    0.75
     redistribution
    0.75
     freely
    0.75
    renheit
    0.72
     modification
    0.71
    ensor
    0.71
    Activations Density 0.081%

    No Known Activations