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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20759
    Prev
    Next
    INDEX
    Explanations

    words related to qualifications or permissions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of credentials and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mast
    -0.70
     Depression
    -0.65
     Bed
    -0.63
    Bed
    -0.63
    hearted
    -0.62
     Sleeping
    -0.62
    ÃŁ
    -0.61
    upon
    -0.61
     Kind
    -0.61
    âĸ¬
    -0.61
    POSITIVE LOGITS
     credentials
    1.80
     credential
    1.11
     qualifications
    0.91
    milo
    0.89
     pedigree
    0.85
     certs
    0.81
    entials
    0.80
     certificates
    0.79
     holders
    0.79
    anooga
    0.78
    Activations Density 0.006%

    No Known Activations