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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    6. 13494
    Prev
    Next
    INDEX
    Explanations

    unrelated symbols and special characters

    oai_token-act-pair · gpt-3.5-turbo

    repeated or unique characters that may indicate presence of special symbols or formatting indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shroud
    -0.72
     handshake
    -0.71
    ahime
    -0.70
     beaut
    -0.68
     bragging
    -0.65
     tongues
    -0.65
     lovers
    -0.65
     casing
    -0.64
     microphone
    -0.64
     smokes
    -0.64
    POSITIVE LOGITS
    ¡
    1.04
    ¤
    1.04
    º
    1.01
    Ĵ
    0.97
    ł
    0.94
    âĢł
    0.92
    µ
    0.91
    ²
    0.90
    ³
    0.89
    bryce
    0.88
    Activations Density 0.363%

    No Known Activations