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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11899
    Prev
    Next
    INDEX
    Explanations

    the name "Gail"

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or bodily harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perature
    -0.62
    aido
    -0.61
     isolate
    -0.60
     WHO
    -0.59
     CPS
    -0.57
     sensitive
    -0.56
     basic
    -0.56
    ngth
    -0.56
     neutral
    -0.56
    opausal
    -0.56
    POSITIVE LOGITS
    ail
    1.17
    ails
    1.02
    runner
    0.91
    Runner
    0.83
    abe
    0.80
    ily
    0.79
    hander
    0.78
    usterity
    0.78
    ouri
    0.72
    runners
    0.71
    Activations Density 0.005%

    No Known Activations