© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 5764
    Prev
    Next
    INDEX
    Explanations

    specific locations, organizations, and titles of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places, organizations, or significant entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.80
    theless
    -0.78
    liest
    -0.75
    skirts
    -0.73
    pieces
    -0.72
    places
    -0.68
    worms
    -0.67
    terday
    -0.66
     needles
    -0.66
    verts
    -0.66
    POSITIVE LOGITS
    onian
    1.11
    ussian
    1.02
    ussie
    0.97
    inian
    0.89
    orian
    0.87
    assian
    0.83
    Tech
    0.80
    western
    0.78
    nian
    0.78
    istine
    0.78
    Activations Density 0.421%

    No Known Activations