© 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 EvalsExportsAPI 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. 7-RES-JB
    11. 20614
    Prev
    Next
    INDEX
    Explanations

    references to someone or something making a comeback or reappearing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "return" and its variants used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iop
    -0.80
    ascript
    -0.76
    urity
    -0.71
    Catalog
    -0.70
    odan
    -0.70
    mination
    -0.69
    Administ
    -0.68
    天
    -0.67
    agate
    -0.67
    ihad
    -0.67
    POSITIVE LOGITS
    ees
    0.86
     home
    0.79
     HOME
    0.68
     istg
    0.68
     unsc
    0.67
     caster
    0.66
     stomp
    0.66
     victorious
    0.65
     kickoff
    0.64
    home
    0.64
    Activations Density 0.065%

    No Known Activations