© 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. 4-RES-JB
    11. 17266
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific brand or product named "FX" with different variations in activations

    oai_token-act-pair · gpt-3.5-turbo

    references to the FX network or its programming

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

    No Comments

    Negative Logits
     Adin
    -0.95
     carcin
    -0.73
     Fas
    -0.69
    izational
    -0.66
    alogue
    -0.66
    chen
    -0.65
     Astro
    -0.65
     Enrique
    -0.65
     McKenna
    -0.64
     Schne
    -0.63
    POSITIVE LOGITS
    FX
    0.93
    erity
    0.88
    ombies
    0.86
    ergus
    0.85
    fx
    0.80
    assi
    0.79
    uries
    0.76
    FP
    0.76
    SW
    0.75
    CG
    0.73
    Activations Density 0.010%

    No Known Activations