© 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. 8-RES-JB
    11. 6378
    Prev
    Next
    INDEX
    Explanations

    special characters surrounded by spaces

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.93
     endeavour
    -0.80
     ageing
    -0.68
     Reincarnated
    -0.67
     ideal
    -0.66
    isable
    -0.66
     endeav
    -0.65
     equip
    -0.64
    lling
    -0.64
    tons
    -0.64
    POSITIVE LOGITS
    ³³³³³³³³
    0.96
    However
    0.95
    Advertisement
    0.94
    Update
    0.94
    Asked
    0.93
    Meanwhile
    0.92
    Nevertheless
    0.91
    Still
    0.90
    ³³³³
    0.89
    UPDATE
    0.88
    Activations Density 0.542%

    No Known Activations