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. 11-RES-JB
    6. 19102
    Prev
    Next
    INDEX
    Explanations

    titles or headings within a structured document

    oai_token-act-pair · gpt-3.5-turbo

    the closing parentheses in various headings or titles

    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
    ively
    -0.69
    bably
    -0.68
    respective
    -0.64
    ¬¼
    -0.64
    Ͻ
    -0.64
    Ĥª
    -0.63
    clus
    -0.60
    ,
    -0.60
    tons
    -0.60
    ,.
    -0.59
    POSITIVE LOGITS
    ↵
    0.98
    ↵↵
    0.91
     Discuss
    0.89
     âĵĺ
    0.88
    <|endoftext|>
    0.88
     =================================================================
    0.84
     Includes
    0.81
    ↵Âł
    0.77
     =================
    0.76
     [*]
    0.75
    Activations Density 0.126%

    No Known Activations