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. 7-RES-JB
    6. 24280
    Prev
    Next
    INDEX
    Explanations

    phrases expressing scenarios where something has not yet been completed or addressed

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "haven" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nearest
    -0.63
     compliment
    -0.62
     fly
    -0.62
     Draw
    -0.61
     guided
    -0.61
     predictor
    -0.60
     heaviest
    -0.59
     flies
    -0.59
     PU
    -0.59
     guid
    -0.59
    POSITIVE LOGITS
    't
    1.33
    ÃŃ
    1.04
    ited
    1.04
    ãĤ§
    0.96
    tyard
    0.88
    iting
    0.88
    earned
    0.88
    dayName
    0.86
    ajor
    0.84
    nas
    0.84
    Activations Density 0.025%

    No Known Activations