© 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. 10-RES-JB
    11. 11004
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a partial reason or cause for something

    oai_token-act-pair · gpt-3.5-turbo

    references to the phrase "in part."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clipboard
    -0.70
     Commissioners
    -0.69
     happiest
    -0.61
     nodd
    -0.60
     hawk
    -0.59
     Rampage
    -0.58
     Keen
    -0.57
     NEXT
    -0.56
    lean
    -0.56
    mins
    -0.55
    POSITIVE LOGITS
    lie
    0.74
     thanks
    0.72
    atos
    0.71
    because
    0.70
     because
    0.70
     due
    0.68
    wagen
    0.68
    rano
    0.64
    icular
    0.63
    spring
    0.62
    Activations Density 0.029%

    No Known Activations