© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6455
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases starting with parentheses, potentially related to technical or specific information within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses and their contents

    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
     tears
    -0.69
     distingu
    -0.69
     oranges
    -0.68
     vom
    -0.65
     Bris
    -0.64
     sadly
    -0.64
     flats
    -0.64
     accomp
    -0.63
     kindly
    -0.63
     looms
    -0.62
    POSITIVE LOGITS
    yet
    1.09
    sounding
    1.08
    albeit
    0.98
    non
    0.93
    atomic
    0.91
    meaning
    0.84
    anti
    0.82
    sic
    0.82
    but
    0.81
    enough
    0.81
    Activations Density 0.247%

    No Known Activations