© 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
    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. 22727
    Prev
    Next
    INDEX
    Explanations

    references to a specific financial institution, 'TD'

    oai_token-act-pair · gpt-3.5-turbo

    references to "TD" and related terms, likely indicating its focus on a specific entity or concept associated with that abbreviation

    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
    eering
    -0.81
    byss
    -0.77
    bidden
    -0.68
    hift
    -0.67
    tics
    -0.67
    packing
    -0.66
    eers
    -0.66
    hold
    -0.66
    oid
    -0.66
    vasive
    -0.64
    POSITIVE LOGITS
    TD
    0.99
    IFF
    0.86
    WP
    0.82
    rees
    0.82
    LR
    0.78
    LC
    0.77
    EE
    0.77
    CHA
    0.77
    NA
    0.76
    cake
    0.76
    Activations Density 0.018%

    No Known Activations