© 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. 21476
    Prev
    Next
    INDEX
    Explanations

    verbs related to assessing, inspecting, or evaluating something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to assessment and evaluation processes

    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
    ãĤª
    -0.66
    Wr
    -0.58
    talk
    -0.55
    pictured
    -0.54
    edes
    -0.54
     Huck
    -0.52
    ede
    -0.52
    chev
    -0.52
     Fant
    -0.52
     Wrong
    -0.51
    POSITIVE LOGITS
     extensively
    1.06
     by
    1.05
     separately
    0.99
     thoroughly
    0.98
     individually
    0.95
     favorably
    0.89
     closely
    0.86
     harshly
    0.85
     positively
    0.82
     vigorously
    0.80
    Activations Density 0.144%

    No Known Activations