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. 4-RES-JB
    6. 20997
    Prev
    Next
    INDEX
    Explanations

    references to numerical rankings/orders

    oai_token-act-pair · gpt-3.5-turbo

    sentences with ranking or scoring information

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

    No Comments

    Negative Logits
    gypt
    -0.77
     herds
    -0.77
     bunny
    -0.73
    issance
    -0.69
     toile
    -0.69
     transact
    -0.68
     unravel
    -0.67
    isine
    -0.63
     rabbit
    -0.63
     bir
    -0.61
    POSITIVE LOGITS
    eous
    0.84
     whatsoever
    0.77
    gov
    0.75
     Accessed
    0.74
    CLASSIFIED
    0.73
    ificant
    0.69
    Downloadha
    0.69
    Org
    0.69
     Ranking
    0.68
    RFC
    0.67
    Activations Density 0.043%

    No Known Activations