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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 12558
    Prev
    Next
    INDEX
    Explanations

    strings of characters that are not in the English alphabet

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols used in textual data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izarre
    -0.71
    alez
    -0.71
    agram
    -0.70
    OWER
    -0.70
    dfx
    -0.70
    ilic
    -0.68
    oscope
    -0.67
    ayson
    -0.66
    ictional
    -0.65
    atively
    -0.65
    POSITIVE LOGITS
     la
    0.90
    ´
    0.88
    ħĭ
    0.80
    Ĭ±
    0.79
    ĭ
    0.78
    VERTISEMENT
    0.77
     Qian
    0.74
    æł
    0.74
    ¯¯¯¯
    0.72
    ¶
    0.70
    Activations Density 0.019%

    No Known Activations