© 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. 0-RES-JB
    11. 13478
    Prev
    Next
    INDEX
    Explanations

    mentions of "CAP" or related words likely in an economic or technical context

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of financial or investment asset, particularly in the context of a discussion about capital or coins

    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
     Rossi
    -0.77
    lly
    -0.76
    ön
    -0.75
    lyak
    -0.73
    ysical
    -0.71
     needles
    -0.71
    terness
    -0.71
    stanbul
    -0.71
     Gong
    -0.70
    orno
    -0.69
    POSITIVE LOGITS
     CAP
    3.07
    capt
    2.60
    CAP
    2.47
    Capt
    2.27
     Capt
    2.23
     captcha
    1.58
     recapt
    1.17
     caps
    1.10
     capt
    1.02
    cap
    1.00
    Activations Density 0.021%

    No Known Activations