© 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. 21632
    Prev
    Next
    INDEX
    Explanations

    descriptions of things being full or filled with something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe something being full or filled with various elements

    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
    OTO
    -0.70
    ordan
    -0.67
    akuya
    -0.63
     commencement
    -0.63
    cott
    -0.60
    atro
    -0.58
    tein
    -0.57
    oker
    -0.57
    tten
    -0.57
    andum
    -0.56
    POSITIVE LOGITS
     with
    1.16
     withd
    0.96
     WITH
    0.95
    with
    0.88
     With
    0.83
    With
    0.77
     by
    0.77
     aback
    0.74
     solely
    0.73
     wi
    0.72
    Activations Density 0.138%

    No Known Activations