© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14343
    Prev
    Next
    INDEX
    Explanations

    names or titles of individuals, particularly ones of high standing or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    references to notable or distinguished individuals

    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
    arella
    -0.82
    akeru
    -0.73
     Airl
    -0.68
     Abyssal
    -0.66
    printf
    -0.65
     Caps
    -0.63
    apa
    -0.63
     Spice
    -0.62
    leton
    -0.62
     Primordial
    -0.61
    POSITIVE LOGITS
     eminent
    0.90
    minent
    0.81
    ignty
    0.79
    inence
    0.75
    urbed
    0.71
    inent
    0.71
    kees
    0.69
    BLE
    0.68
    icter
    0.68
     interven
    0.68
    Activations Density 0.010%

    No Known Activations