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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10138
    Prev
    Next
    INDEX
    Explanations

    instances of similarity or likenesses between different entities or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to similar events or occurrences

    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
    arest
    -0.78
    OST
    -0.75
    hest
    -0.74
    real
    -0.71
    gemony
    -0.70
    Diamond
    -0.69
    arden
    -0.68
    friends
    -0.68
    nos
    -0.68
    ribution
    -0.67
    POSITIVE LOGITS
     sized
    1.20
     sentiments
    1.10
     minded
    1.10
     fate
    1.07
    lihood
    1.06
     vein
    1.03
    ities
    0.99
     reasoning
    0.93
     phenomena
    0.93
    worldly
    0.90
    Activations Density 0.050%

    No Known Activations