© 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. 2-RES-JB
    11. 24141
    Prev
    Next
    INDEX
    Explanations

    references to Creative Commons licenses

    oai_token-act-pair · gpt-3.5-turbo

    references to Creative Commons licensing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samoa
    -0.75
     Giuliani
    -0.68
    ãĤ¶
    -0.67
    oti
    -0.67
    ths
    -0.66
    Iraq
    -0.65
    iasis
    -0.63
     Mankind
    -0.63
     Languages
    -0.62
    antly
    -0.62
    POSITIVE LOGITS
     CC
    0.89
    lean
    0.87
    CCC
    0.83
    olor
    0.78
    aution
    0.76
    CC
    0.73
    ritical
    0.70
    ombat
    0.70
    enhagen
    0.69
     jumper
    0.69
    Activations Density 0.005%

    No Known Activations