© 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. 7101
    Prev
    Next
    INDEX
    Explanations

    terms related to relationships, connections, and associations between entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social connections and group affiliations

    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
     Scotia
    -0.69
    ASED
    -0.64
     VIDE
    -0.63
    OUT
    -0.61
     bye
    -0.60
    OPLE
    -0.60
     Germ
    -0.60
     Pwr
    -0.59
     conscience
    -0.59
     EDIT
    -0.59
    POSITIVE LOGITS
    hip
    2.53
    hips
    2.13
    uit
    1.29
    uits
    1.25
    ystem
    1.17
    pring
    1.15
    atile
    1.14
    hops
    1.11
    manship
    1.11
    pace
    1.07
    Activations Density 0.087%

    No Known Activations