© 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. 4-RES-JB
    11. 15305
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "substantiated."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to unsubstantiated claims or allegations

    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
    giving
    -0.89
     marrow
    -0.77
    jack
    -0.76
    keeper
    -0.73
     tender
    -0.70
    Pear
    -0.70
    keepers
    -0.69
    lder
    -0.69
    UC
    -0.67
    ocamp
    -0.67
    POSITIVE LOGITS
    iated
    1.30
    ially
    1.13
    iating
    1.05
    iate
    1.01
    iation
    1.01
    rons
    0.98
    imated
    0.96
    iates
    0.95
    etric
    0.91
    etrical
    0.88
    Activations Density 0.012%

    No Known Activations