© 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. 3-RES-JB
    11. 11391
    Prev
    Next
    INDEX
    Explanations

    mentions of films

    oai_token-act-pair · gpt-3.5-turbo

    mentions of films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FUL
    -0.69
     legislature
    -0.63
     politic
    -0.61
    ife
    -0.60
    GY
    -0.60
     subsistence
    -0.60
     sergeant
    -0.59
    owder
    -0.59
     wheelchair
    -0.59
    fac
    -0.58
    POSITIVE LOGITS
    uggest
    0.94
    earch
    0.93
    ystem
    0.92
    ensitive
    0.90
     movies
    0.90
    ilver
    0.89
    linger
    0.88
     films
    0.88
    ynthesis
    0.88
    ettings
    0.86
    Activations Density 0.043%

    No Known Activations