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. 7-RES-JB
    6. 20129
    Prev
    Next
    INDEX
    Explanations

    comparative terms related to improvement or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating improvement or value enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lees
    -0.95
    coins
    -0.92
    events
    -0.90
    guards
    -0.84
     wards
    -0.81
    casts
    -0.76
    marks
    -0.76
    upon
    -0.74
    notes
    -0.74
    hops
    -0.74
    POSITIVE LOGITS
     version
    1.10
    iator
    1.01
     option
    0.96
     picture
    0.95
     solution
    0.94
     timeframe
    0.92
     proposition
    0.91
     swath
    0.91
     subset
    0.91
     timetable
    0.90
    Activations Density 0.104%

    No Known Activations