© 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. 7-RES-JB
    11. 24173
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location or place, specifically "Co"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity associated with 'Co'

    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
     IMAGES
    -0.75
     GOODMAN
    -0.73
    lihood
    -0.72
    ICAN
    -0.70
     guiActiveUn
    -0.64
     Hungarian
    -0.63
    TING
    -0.60
     Trou
    -0.60
    acious
    -0.58
     Sut
    -0.58
    POSITIVE LOGITS
    aching
    1.11
    venants
    1.11
    ffe
    1.10
    aches
    1.09
    vern
    1.06
    verage
    1.06
    vers
    1.04
    herent
    1.03
    asters
    1.03
    ffee
    1.03
    Activations Density 0.031%

    No Known Activations