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. 6-RES-JB
    6. 22087
    Prev
    Next
    INDEX
    Explanations

    words related to technology and communication methods, particularly those involving links or website references

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the slash (/) symbol

    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
     redes
    -0.68
     obliged
    -0.65
     crawl
    -0.65
    terness
    -0.63
     expans
    -0.60
    chwitz
    -0.59
    agos
    -0.58
    ibaba
    -0.58
     bom
    -0.57
    omorph
    -0.57
    POSITIVE LOGITS
    friends
    0.69
    cases
    0.69
    won
    0.69
    drawn
    0.68
    OUT
    0.68
    tips
    0.67
    holding
    0.67
    models
    0.67
    o
    0.66
    some
    0.66
    Activations Density 0.018%

    No Known Activations