© 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. 0-RES-JB
    11. 5385
    Prev
    Next
    INDEX
    Explanations

    terms related to annual events or financial growth

    oai_token-act-pair · gpt-3.5-turbo

    mentions of annual reports or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %]
    -0.70
    fg
    -0.63
    BuyableInstoreAndOnline
    -0.61
     reg
    -0.60
    iw
    -0.60
     Osiris
    -0.59
    Slot
    -0.58
     Yanuk
    -0.58
     Goo
    -0.57
    Jet
    -0.56
    POSITIVE LOGITS
    zz
    0.69
     paternity
    0.68
    pend
    0.66
    igi
    0.64
    onds
    0.63
    wright
    0.62
    nutrition
    0.62
    toe
    0.61
    sequ
    0.60
    license
    0.60
    Activations Density 0.000%

    No Known Activations