© 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. 1-RES-JB
    6. 7960
    Prev
    Next
    INDEX
    Explanations

    special characters within a text or code

    oai_token-act-pair · gpt-3.5-turbo

    patterns or sequences of backslashes and characters resembling coding or technical syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.83
    ascus
    -0.78
     assassins
    -0.74
     shot
    -0.73
     insult
    -0.72
    theless
    -0.72
    itcher
    -0.70
     therap
    -0.69
     undermin
    -0.69
     Palestin
    -0.67
    POSITIVE LOGITS
    AppData
    1.04
    (\
    1.03
    wcsstore
    1.00
    circ
    0.94
    root
    0.92
    sq
    0.91
    gradient
    0.91
    framework
    0.90
    \'
    0.89
    bryce
    0.87
    Activations Density 0.005%

    No Known Activations