© 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. 11043
    Prev
    Next
    INDEX
    Explanations

    names of a person "Haney"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, likely related to a notable event or situation

    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
    ivity
    -0.92
    spring
    -0.72
    ional
    -0.69
    icably
    -0.68
    ually
    -0.67
    ests
    -0.67
     pity
    -0.65
    agonist
    -0.64
    ories
    -0.64
    inate
    -0.62
    POSITIVE LOGITS
    hyde
    0.93
    geon
    0.89
    aney
    0.87
    stal
    0.79
    berry
    0.77
    clips
    0.76
    ffe
    0.74
    combe
    0.73
    loe
    0.71
    hawk
    0.70
    Activations Density 0.016%

    No Known Activations