© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 14758
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific town called "Bournemouth."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ourn" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rossi
    -0.73
    FU
    -0.65
     Consent
    -0.64
     Sapphire
    -0.63
    Effective
    -0.62
    Wan
    -0.62
    ebra
    -0.61
     Eston
    -0.60
    BIP
    -0.59
    plates
    -0.59
    POSITIVE LOGITS
    emouth
    1.43
    oir
    1.16
    ourn
    1.09
    ette
    1.02
    ettes
    1.00
    ments
    0.99
    oise
    0.97
    shire
    0.95
    nette
    0.93
    esses
    0.92
    Activations Density 0.013%

    No Known Activations