© 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. 9703
    Prev
    Next
    INDEX
    Explanations

    actions related to the revocation, suspension, or cessation of programs, policies, or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    verbs related to decisions and actions

    oai_token-act-pair · gpt-3.5-turbo
    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
    Craft
    -0.90
    aceae
    -0.83
    achine
    -0.73
    ebus
    -0.71
    quart
    -0.70
    doi
    -0.69
    ixture
    -0.68
    inside
    -0.68
    swick
    -0.67
    METHOD
    -0.67
    POSITIVE LOGITS
     banning
    0.81
     banned
    0.80
     indefinite
    0.77
     offending
    0.76
     unnecessary
    0.76
     bans
    0.76
     discriminatory
    0.75
     refunds
    0.74
     disqual
    0.73
     susp
    0.73
    Activations Density 0.249%

    No Known Activations