Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3827
    Prev
    Next
    INDEX
    Explanations

    instances of non-English characters

    oai_token-act-pair · gpt-3.5-turbo

    non-standard characters and symbols

    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
    nesota
    -0.76
    clair
    -0.76
    ajo
    -0.74
     handshake
    -0.70
    espie
    -0.69
     liaison
    -0.67
    utenberg
    -0.66
    emetery
    -0.66
    assador
    -0.66
     curiosity
    -0.66
    POSITIVE LOGITS
    Ĭ
    1.56
    天
    1.10
    ĭ
    1.05
    Ĩ
    1.04
    ł
    1.03
    âĶĢâĶĢ
    1.02
    ¶
    1.02
    س
    1.02
    Ùİ
    1.00
    «
    1.00
    Activations Density 0.005%

    No Known Activations