Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15578
    Prev
    Next
    INDEX
    Explanations

    texts or mentions related to the term "FX"

    oai_token-act-pair · gpt-3.5-turbo

    references to the FX television network

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adin
    -0.89
     Astro
    -0.69
     captcha
    -0.69
     carcin
    -0.67
     Fas
    -0.66
    chen
    -0.65
     Autism
    -0.65
    izational
    -0.64
     socialist
    -0.64
    inated
    -0.62
    POSITIVE LOGITS
    FX
    0.95
    ergus
    0.91
    fx
    0.84
    erity
    0.82
    SW
    0.77
    rites
    0.76
    VI
    0.75
    Works
    0.74
    assi
    0.74
    ombies
    0.73
    Activations Density 0.016%

    No Known Activations