© 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. 18001
    Prev
    Next
    INDEX
    Explanations

    information related to income levels and financial situations

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts and income-related statistics

    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
    ãĥ³ãĤ¸
    -0.64
     Nish
    -0.64
     Izan
    -0.63
    "]=>
    -0.62
    MET
    -0.61
     Vald
    -0.61
    ãĥķãĤ©
    -0.60
     Mazda
    -0.60
    hiro
    -0.60
    Tes
    -0.59
    POSITIVE LOGITS
     backgrounds
    0.78
     qualify
    0.77
     or
    0.70
     ineligible
    0.70
    ulia
    0.70
     (>
    0.69
     qualifying
    0.69
     qualifies
    0.68
    ptives
    0.67
    artifacts
    0.66
    Activations Density 0.798%

    No Known Activations