© 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. 9-RES-JB
    11. 2440
    Prev
    Next
    INDEX
    Explanations

    disclaimers or statements indicating a lack of endorsement or affiliation with certain views or entities

    oai_token-act-pair · gpt-3.5-turbo
    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
    footed
    -0.71
    noticed
    -0.70
     yawn
    -0.70
     jaws
    -0.69
     basics
    -0.68
     plenty
    -0.66
     barely
    -0.63
    kens
    -0.63
     Finding
    -0.61
    pretty
    -0.60
    POSITIVE LOGITS
     condone
    1.22
     affiliated
    0.90
     endorse
    0.89
    nor
    0.89
     nor
    0.87
     endorsement
    0.84
     endorsed
    0.80
    soever
    0.79
     LIA
    0.78
     imply
    0.77
    Activations Density 0.341%

    No Known Activations