© 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. 1-RES-JB
    11. 24031
    Prev
    Next
    INDEX
    Explanations

    prepositions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inclusion or being part of a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.73
    theless
    -0.71
    cast
    -0.68
    pull
    -0.67
    boards
    -0.66
    picking
    -0.66
    craft
    -0.63
    Pull
    -0.63
    tenance
    -0.62
     Ferry
    -0.61
    POSITIVE LOGITS
    ersen
    0.79
    ocry
    0.77
    repre
    0.74
    regn
    0.72
    ulic
    0.72
    assian
    0.70
    helle
    0.70
    ieu
    0.69
    enburg
    0.69
    encia
    0.68
    Activations Density 0.000%

    No Known Activations