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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 3-RES-JB
    6. 14556
    Prev
    Next
    INDEX
    Explanations

    words related to achieving success or being successful

    oai_token-act-pair · gpt-3.5-turbo

    terms related to success and achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FACE
    -0.74
     sequest
    -0.72
     dearly
    -0.65
     euth
    -0.62
     reserv
    -0.61
     Sawyer
    -0.61
     innoc
    -0.61
     suppose
    -0.60
    åĤ
    -0.59
     err
    -0.59
    POSITIVE LOGITS
    ful
    1.41
    fully
    1.30
    isters
    0.96
    ories
    0.95
    emouth
    0.92
    ion
    0.89
    iola
    0.86
    full
    0.86
    udos
    0.85
    fulness
    0.84
    Activations Density 0.015%

    No Known Activations