© 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. 9-RES-JB
    11. 11433
    Prev
    Next
    INDEX
    Explanations

    words related to financial terms or transactions

    oai_token-act-pair · gpt-3.5-turbo

    patterns or references to the word "ven"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FTA
    -0.72
    ERC
    -0.63
     rgb
    -0.60
    fair
    -0.60
    onse
    -0.59
    alach
    -0.58
    enfranch
    -0.58
    earance
    -0.58
    haps
    -0.57
     envy
    -0.57
    POSITIVE LOGITS
    ski
    1.12
    sky
    1.10
    ger
    1.06
    s
    0.98
    sie
    0.97
    gers
    0.96
    cy
    0.90
    sk
    0.90
    ging
    0.89
    ues
    0.88
    Activations Density 0.046%

    No Known Activations