© 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. 11081
    Prev
    Next
    INDEX
    Explanations

    words related to producing or returning specific outcomes/results

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the accuracy and effectiveness of algorithms or systems

    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
    aran
    -0.68
    ahime
    -0.67
    occup
    -0.67
    aldo
    -0.67
    chool
    -0.66
    onto
    -0.66
     Ezek
    -0.66
    enture
    -0.63
    inventory
    -0.63
    obil
    -0.61
    POSITIVE LOGITS
     results
    1.39
     satisfactory
    1.18
     optimal
    1.07
     conclusions
    1.06
    results
    1.05
     optimum
    1.04
     usable
    1.00
     identical
    0.99
     accurate
    0.97
     superior
    0.94
    Activations Density 0.293%

    No Known Activations