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. 4-RES-JB
    6. 23476
    Prev
    Next
    INDEX
    Explanations

    unrelated symbols and words, potentially related to coding or errors in text processing

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific symbol or character representation

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

    No Comments

    Negative Logits
    uay
    -0.70
     apes
    -0.70
     metic
    -0.67
     tremend
    -0.66
     misunder
    -0.66
     bun
    -0.66
    alien
    -0.64
     deed
    -0.64
     fragmentation
    -0.63
     Zeit
    -0.63
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.06
    ï¸ı
    0.96
    âĶĢâĶĢâĶĢâĶĢ
    0.88
    lean
    0.84
    uthor
    0.82
    ternity
    0.80
    âĵĺ
    0.79
    null
    0.78
    âĢł
    0.78
    athom
    0.78
    Activations Density 0.236%

    No Known Activations