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. 3-RES-JB
    6. 14440
    Prev
    Next
    INDEX
    Explanations

    short strings that include the word "work" as a part of a larger word or name

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the term 'ork' in various forms

    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
    ples
    -0.75
     tradem
    -0.65
    cit
    -0.62
     vanilla
    -0.61
     cardio
    -0.59
     charity
    -0.58
     behavi
    -0.58
    ciples
    -0.57
    EVA
    -0.56
    cence
    -0.56
    POSITIVE LOGITS
    ansas
    1.15
    hire
    0.94
    ozy
    0.91
    lift
    0.89
    patrick
    0.85
    osaurus
    0.84
    enhagen
    0.82
    ork
    0.81
    atana
    0.80
    owski
    0.80
    Activations Density 0.004%

    No Known Activations