© 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. 10-RES-JB
    11. 18626
    Prev
    Next
    INDEX
    Explanations

    terms related to financial activities, such as "buybacks" and "sell-offs"

    oai_token-act-pair · gpt-3.5-turbo

    financial terms related to buying and selling actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monstrous
    -0.76
     Aven
    -0.68
     Sind
    -0.62
     Pione
    -0.62
    ĺħ
    -0.62
     Princ
    -0.58
     Sett
    -0.57
     Mund
    -0.57
     Curious
    -0.57
    IZE
    -0.57
    POSITIVE LOGITS
    outs
    1.42
    backs
    1.27
    aways
    1.26
    ups
    1.20
    overs
    1.19
    downs
    1.18
    away
    1.17
    ings
    1.17
    offs
    1.17
    out
    1.12
    Activations Density 0.259%

    No Known Activations