© 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. 3-RES-JB
    6. 8884
    Prev
    Next
    INDEX
    Explanations

    code syntax related to programming

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax elements and operators

    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
    ĸļ
    -0.81
     paran
    -0.78
     puberty
    -0.77
    hement
    -0.77
     submar
    -0.75
     outwe
    -0.74
     veter
    -0.74
     ambassadors
    -0.71
     advoc
    -0.71
     enthusi
    -0.70
    POSITIVE LOGITS
    Output
    1.13
    };
    1.04
    */
    1.04
    Example
    1.02
    Usage
    0.99
    """
    0.99
    /*
    0.93
    {{
    0.92
    parse
    0.90
    }}
    0.90
    Activations Density 0.178%

    No Known Activations