© 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. 10770
    Prev
    Next
    INDEX
    Explanations

    specific pieces or items in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "piece of" followed by various nouns

    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
    uations
    -0.89
    essors
    -0.83
    ancies
    -0.79
    ivals
    -0.77
    racuse
    -0.75
    inas
    -0.75
    artments
    -0.74
    rils
    -0.74
    ours
    -0.73
     GOODMAN
    -0.73
    POSITIVE LOGITS
     equipment
    1.02
     legislation
    1.01
     advice
    0.97
     trivia
    0.96
     cake
    0.94
     furniture
    0.92
     scenery
    0.90
     machinery
    0.89
     evidence
    0.88
     hardware
    0.88
    Activations Density 0.066%

    No Known Activations