© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19782
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Here at" followed by a location or company name

    oai_token-act-pair · gpt-3.5-turbo

    locations and references to various places

    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
    76561
    -0.80
    establishment
    -0.69
    susp
    -0.66
     sshd
    -0.64
    emo
    -0.64
    ensibly
    -0.62
    Malley
    -0.61
    RM
    -0.61
    Interest
    -0.61
    phen
    -0.59
    POSITIVE LOGITS
    swick
    0.85
     Nieto
    0.78
    ffield
    0.68
    abad
    0.68
    nyder
    0.66
    igans
    0.65
     plead
    0.65
    女
    0.64
    nesday
    0.62
    iate
    0.62
    Activations Density 0.181%

    No Known Activations