© 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. 7-RES-JB
    6. 11482
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific entity named "Bell"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Bell."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    visor
    -0.72
    joining
    -0.70
    bered
    -0.66
    PLIED
    -0.66
    JUST
    -0.65
    llers
    -0.65
    rers
    -0.65
     Gallup
    -0.62
    ~~~~~~~~
    -0.61
    ACTION
    -0.61
    POSITIVE LOGITS
    ows
    1.09
    ichick
    1.09
    ingham
    1.02
    amy
    1.02
    anca
    0.91
    bone
    0.87
    otti
    0.85
    iard
    0.83
    spr
    0.83
    inger
    0.83
    Activations Density 0.019%

    No Known Activations