© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 9522
    Prev
    Next
    INDEX
    Explanations

    non-standard characters that might be part of a specific language or code

    oai_token-act-pair · gpt-3.5-turbo

    the character 'ļ'

    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
    ebus
    -0.83
    emouth
    -0.79
    ovie
    -0.75
    geist
    -0.75
    omers
    -0.75
    esan
    -0.74
    anooga
    -0.73
    estine
    -0.73
    hran
    -0.73
    merce
    -0.73
    POSITIVE LOGITS
    âķIJâķIJ
    1.28
    ļ
    1.28
    Ĺ
    1.20
    ा
    1.19
    âķIJ
    1.17
    ł
    0.97
    à¥
    0.97
    ®
    0.96
    «
    0.96
    LEY
    0.96
    Activations Density 0.008%

    No Known Activations