© 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. 9835
    Prev
    Next
    INDEX
    Explanations

    the surname "En" with varying levels of specificity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "en"

    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
     hitch
    -0.62
     unrecogn
    -0.61
     Canaveral
    -0.61
     unfavorable
    -0.58
     unnamed
    -0.58
     exceptional
    -0.57
     aborted
    -0.57
     humor
    -0.57
     Nicarag
    -0.56
     humour
    -0.56
    POSITIVE LOGITS
    bach
    1.32
    baum
    1.29
    heimer
    1.28
    berger
    1.23
    esis
    1.20
    wald
    1.19
    baugh
    1.15
    feld
    1.13
    zyme
    1.12
    burgh
    1.11
    Activations Density 0.084%

    No Known Activations