Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3255
    Prev
    Next
    INDEX
    Explanations

    snippets of code or programming-related terms

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to coding, race, and social identity

    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
    raft
    -0.60
     Panic
    -0.59
    jam
    -0.58
    ruce
    -0.58
    icion
    -0.57
     announces
    -0.57
     IRC
    -0.56
     Emails
    -0.54
    sers
    -0.53
     lockout
    -0.53
    POSITIVE LOGITS
     biologically
    0.67
    sexual
    0.66
     nudity
    0.64
     ancest
    0.61
    ulnerability
    0.60
     ethnic
    0.58
     biological
    0.58
     Attributes
    0.57
    complex
    0.56
     culturally
    0.56
    Activations Density 1.582%

    No Known Activations