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. 3-RES-JB
    6. 8490
    Prev
    Next
    INDEX
    Explanations

    names and words related to specific individuals such as "Harley" and "Haron"

    oai_token-act-pair · gpt-3.5-turbo

    words related to harvesting and academic institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İĭ
    -0.84
     guarant
    -0.68
    ©¶æ
    -0.66
    ctors
    -0.65
    emort
    -0.64
    ortium
    -0.64
    rongh
    -0.62
     subp
    -0.62
    versely
    -0.61
    redo
    -0.61
    POSITIVE LOGITS
    schild
    0.83
     Annotations
    0.76
    ette
    0.75
    ettes
    0.69
    dash
    0.68
    cliffe
    0.66
    ã
    0.65
    ricanes
    0.64
    oola
    0.63
     Mum
    0.62
    Activations Density 0.133%

    No Known Activations