© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15346
    Prev
    Next
    INDEX
    Explanations

    specific words related to a particular term, "Bonanza"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific film titles and the associated context of "Citizen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rained
    -0.80
     caste
    -0.77
     induction
    -0.69
     caster
    -0.69
    PLIED
    -0.67
     honorary
    -0.67
     wheelchair
    -0.65
     robe
    -0.65
     jeans
    -0.64
     muscles
    -0.63
    POSITIVE LOGITS
    anza
    3.49
    anz
    2.84
     los
    1.26
    asar
    1.08
    zar
    1.05
    enz
    1.03
    rophe
    1.01
    antz
    0.98
     Contra
    0.93
    aban
    0.88
    Activations Density 0.040%

    No Known Activations