© 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. 10045
    Prev
    Next
    INDEX
    Explanations

    expressions related to persistence or ongoing actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to emotional states or feelings

    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
    pecially
    -0.70
    orthy
    -0.69
    default
    -0.66
    icularly
    -0.62
    hash
    -0.62
    brainer
    -0.62
    ibrary
    -0.61
    zac
    -0.61
    mington
    -0.59
    alde
    -0.58
    POSITIVE LOGITS
     still
    2.14
    still
    1.73
     nevertheless
    1.66
     remains
    1.60
     persists
    1.53
     nonetheless
    1.53
     remain
    1.50
     continue
    1.46
     remained
    1.41
     continues
    1.41
    Activations Density 0.669%

    No Known Activations