© 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. 9399
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "roll" and its variations in multiple contexts

    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
    selage
    -0.71
    ĺħ
    -0.69
    ILE
    -0.68
    minist
    -0.66
    liest
    -0.64
    orial
    -0.63
    EMP
    -0.61
    raints
    -0.61
    ulia
    -0.61
    unal
    -0.60
    POSITIVE LOGITS
    icking
    0.94
     dice
    0.92
    back
    0.87
     boulder
    0.85
    over
    0.82
    mington
    0.79
     oats
    0.78
     hills
    0.76
     downhill
    0.75
    backs
    0.74
    Activations Density 0.051%

    No Known Activations