© 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. 5478
    Prev
    Next
    INDEX
    Explanations

    file types such as PNG or actions related to uploading and sharing documents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to negative experiences or undesirable situations

    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
     casting
    -0.73
     cutting
    -0.66
     Paddock
    -0.65
     sidx
    -0.65
     shedding
    -0.63
     Cutting
    -0.61
     verified
    -0.58
    untled
    -0.57
     Horowitz
    -0.56
     drastic
    -0.55
    POSITIVE LOGITS
    whatever
    1.05
    cell
    0.93
    etc
    0.90
    dri
    0.88
    distance
    0.85
    comments
    0.84
    dist
    0.83
    type
    0.82
    alist
    0.81
    factor
    0.81
    Activations Density 0.124%

    No Known Activations