© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7047
    Prev
    Next
    INDEX
    Explanations

    prices and monetary values

    oai_token-act-pair · gpt-3.5-turbo

    numeric values associated with statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unci
    -0.68
     citiz
    -0.66
     frontline
    -0.66
     advers
    -0.65
     relations
    -0.64
     tending
    -0.63
     overcoming
    -0.61
     pse
    -0.61
     clen
    -0.59
     princ
    -0.59
    POSITIVE LOGITS
    -$
    1.15
    USD
    1.04
    /$
    0.99
     USD
    0.98
     MILL
    0.90
     Billion
    0.88
    AU
    0.84
     BELOW
    0.82
     Donation
    0.80
    2500
    0.80
    Activations Density 0.103%

    No Known Activations