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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15971
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically those starting with the letters "Con"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Con" in various contexts

    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
     downhill
    -0.66
     disadvantage
    -0.62
     htt
    -0.62
     abroad
    -0.62
     transpl
    -0.61
     videot
    -0.60
     beh
    -0.59
     retri
    -0.58
     aim
    -0.58
     downside
    -0.57
    POSITIVE LOGITS
    crete
    1.31
    nell
    1.25
    ventional
    1.24
    sequence
    1.22
    venient
    1.22
    nery
    1.20
    secut
    1.17
    cerning
    1.16
    undrum
    1.14
    clusions
    1.13
    Activations Density 0.017%

    No Known Activations