© 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. 6631
    Prev
    Next
    INDEX
    Explanations

    definitions or explanations of terms, concepts, or actions

    oai_token-act-pair · gpt-3.5-turbo

    definitions and concepts related to social and behavioral science

    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
     Hort
    -0.70
    lez
    -0.68
    ··
    -0.66
    daq
    -0.66
     Rapp
    -0.63
    Wonder
    -0.61
     Carbuncle
    -0.61
     Volcano
    -0.61
     Veter
    -0.61
     Vet
    -0.61
    POSITIVE LOGITS
     abbre
    0.94
     grouping
    0.92
     shorthand
    0.84
     whereby
    0.82
     inability
    0.80
     term
    0.79
     tendency
    0.79
     defined
    0.78
     intentional
    0.77
     ability
    0.77
    Activations Density 0.371%

    No Known Activations