© 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. 6-RES-JB
    11. 5047
    Prev
    Next
    INDEX
    Explanations

    terms related to public statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of commentary or remarks made by individuals, particularly in a contentious or newsworthy context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISH
    -0.75
     Recon
    -0.70
    PG
    -0.68
    fruit
    -0.67
    BLIC
    -0.66
    YP
    -0.63
     Rescue
    -0.62
     Brill
    -0.62
     Cav
    -0.60
     resin
    -0.60
    POSITIVE LOGITS
     uttered
    1.01
     comments
    0.90
     remarks
    0.89
     guiActiveUn
    0.82
     aloud
    0.81
    ariat
    0.77
     dispar
    0.72
     slurs
    0.71
    storms
    0.69
    aturday
    0.69
    Activations Density 0.061%

    No Known Activations