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

    Neuronpedia

    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. 3-RES-JB
    11. 12408
    Prev
    Next
    INDEX
    Explanations

    gentle-adjectives

    oai_token-act-pair · gpt-3.5-turbo

    the word "gent" in various contexts

    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
    esty
    -0.80
    ecause
    -0.79
    OIL
    -0.79
    ©¶æ
    -0.78
    ned
    -0.77
    thia
    -0.74
    nington
    -0.74
    WT
    -0.73
    ivia
    -0.70
    amac
    -0.69
    POSITIVE LOGITS
    gent
    1.08
    rants
    0.81
    rant
    0.79
    ente
    0.74
    rification
    0.74
    hal
    0.71
    rieved
    0.69
    lus
    0.66
    Exit
    0.66
    é¾įå¥ij士
    0.65
    Activations Density 0.009%

    No Known Activations