© 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. 2-RES-JB
    11. 6477
    Prev
    Next
    INDEX
    Explanations

    words related to negative outcomes or potential dangers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stall
    -0.73
    aneous
    -0.72
    utions
    -0.69
    tons
    -0.67
    inas
    -0.67
    rine
    -0.66
    meter
    -0.66
    dale
    -0.66
    Db
    -0.65
    encers
    -0.64
    POSITIVE LOGITS
     doom
    0.82
    nown
    0.79
     moth
    0.77
    lessness
    0.74
     è£ıè
    0.73
    emonic
    0.73
     nomine
    0.70
    vertisement
    0.69
    ening
    0.68
    roid
    0.68
    Activations Density 0.032%

    No Known Activations