© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 11081
    Prev
    Next
    INDEX
    Explanations

    instances where the letter "C" with a diacritical mark appears

    oai_token-act-pair · gpt-3.5-turbo

    sequences of code or programming-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -1.01
    ĸļ
    -0.96
     honoured
    -0.73
     ambassadors
    -0.73
     outwe
    -0.73
    Ń·
    -0.72
     answ
    -0.72
     undermin
    -0.71
     submar
    -0.71
    xual
    -0.70
    POSITIVE LOGITS
    Usage
    1.13
    */
    1.10
    Example
    1.07
    Methods
    1.03
    Output
    0.98
    };
    0.96
    References
    0.95
    Serial
    0.94
    Filename
    0.93
    API
    0.93
    Activations Density 0.458%

    No Known Activations