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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 15341
    Prev
    Next
    INDEX
    Explanations

    proper names of people or locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or indicators of urgency in a report

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     undermin
    -0.82
     eleph
    -0.77
    aditional
    -0.76
     gearing
    -0.71
     helicop
    -0.69
     tremend
    -0.68
     exting
    -0.65
    aeda
    -0.63
    senal
    -0.63
    ortunately
    -0.62
    POSITIVE LOGITS
    Investigators
    0.84
    Police
    0.79
    \":
    0.79
    Officers
    0.77
    Neigh
    0.76
    Detect
    0.75
    Authorities
    0.74
    sonian
    0.70
    ↵
    0.69
    Scroll
    0.67
    Activations Density 0.472%

    No Known Activations