© 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. 16239
    Prev
    Next
    INDEX
    Explanations

    terms related to the prefix "hom" followed by a varying number of succeeding characters

    oai_token-act-pair · gpt-3.5-turbo

    references to the genus Homo, particularly in a biological or anthropological context

    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
    FUL
    -0.79
    CLASSIFIED
    -0.79
    FORE
    -0.77
    ESSION
    -0.73
    AMS
    -0.72
    REE
    -0.71
    576
    -0.71
    BuyableInstoreAndOnline
    -0.69
    Accessory
    -0.69
    UGE
    -0.68
    POSITIVE LOGITS
    estead
    1.36
    onym
    1.26
    ogeneity
    1.18
    ogenous
    1.17
    ogeneous
    1.17
    icidal
    1.03
    ozyg
    1.02
    ogen
    0.98
    onymous
    0.96
    oph
    0.96
    Activations Density 0.005%

    No Known Activations