© 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. 11-RES-JB
    11. 20701
    Prev
    Next
    INDEX
    Explanations

    names of businesses and brands

    oai_token-act-pair · gpt-3.5-turbo

    lists of companies or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipeg
    -0.85
    cffffcc
    -0.81
    osexual
    -0.79
    employment
    -0.76
     therapy
    -0.74
    tarian
    -0.73
    umbnails
    -0.73
    cise
    -0.73
    philis
    -0.71
    sex
    -0.69
    POSITIVE LOGITS
     Sigma
    1.22
     Panasonic
    1.16
     Opt
    1.13
     NEC
    1.11
     Siem
    1.11
     Corsair
    1.10
     Adidas
    1.09
     Rite
    1.09
     Philips
    1.08
     Asus
    1.07
    Activations Density 0.240%

    No Known Activations