© 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. 2498
    Prev
    Next
    INDEX
    Explanations

    verbs related to learning, acquiring knowledge, or gaining insights from various sources or experiences

    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
    inois
    -0.66
    pour
    -0.65
     plotted
    -0.64
    Released
    -0.63
    opoulos
    -0.62
    cember
    -0.61
    ription
    -0.60
    oxic
    -0.60
     teasp
    -0.60
    ÄŁ
    -0.58
    POSITIVE LOGITS
     whichever
    1.13
     them
    0.97
     whatever
    0.93
    erous
    0.86
     oneself
    0.86
    effic
    0.82
     whoever
    0.80
    omever
    0.79
     somebody
    0.78
     afar
    0.78
    Activations Density 0.479%

    No Known Activations