© 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. 21775
    Prev
    Next
    INDEX
    Explanations

    instances of the word "deposit" alongside variations like "deposited," "depositor," and "deposits."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bank deposits and depositors

    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
    nen
    -0.73
    ĪĴ
    -0.72
    eyes
    -0.70
    neutral
    -0.65
    DOM
    -0.64
    generic
    -0.60
    icz
    -0.60
    GROUP
    -0.60
    quit
    -0.60
     Machina
    -0.59
    POSITIVE LOGITS
     deposit
    1.16
     Deposit
    1.09
     deposits
    1.06
    osit
    0.99
    holders
    0.94
    iture
    0.92
    itures
    0.90
    ription
    0.90
    ories
    0.89
     receipts
    0.88
    Activations Density 0.030%

    No Known Activations