© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 20927
    Prev
    Next
    INDEX
    Explanations

    terms related to qualifications or permissions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "credentials" and related discussions about qualifications or authentication

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

    No Comments

    Negative Logits
    trap
    -0.64
    sam
    -0.63
    Pause
    -0.63
    ctive
    -0.60
     Mast
    -0.60
    axy
    -0.59
    pen
    -0.59
     Refuge
    -0.59
     wonder
    -0.58
    noon
    -0.58
    POSITIVE LOGITS
     credentials
    1.35
     holders
    0.90
     holder
    0.84
     credential
    0.81
    holder
    0.81
    holders
    0.80
     qualifications
    0.79
     badges
    0.79
     certificates
    0.75
    milo
    0.74
    Activations Density 0.020%

    No Known Activations