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. 2-RES-JB
    6. 19219
    Prev
    Next
    INDEX
    Explanations

    instances where someone or something achieves success or a goal

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "succeed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Origin
    -0.75
    origin
    -0.66
    cars
    -0.65
    Origin
    -0.65
    view
    -0.65
    collection
    -0.65
    phone
    -0.65
    seed
    -0.63
     Stockholm
    -0.62
    den
    -0.61
    POSITIVE LOGITS
     succeed
    0.99
     succeeds
    0.92
    rupal
    0.79
    anke
    0.79
    ceed
    0.78
    ilib
    0.75
    iciary
    0.74
     succeeded
    0.73
    icient
    0.73
    TAIN
    0.71
    Activations Density 0.008%

    No Known Activations