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. 4-RES-JB
    6. 345
    Prev
    Next
    INDEX
    Explanations

    mentions of helicopters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "helicopter."

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

    No Comments

    Negative Logits
    furt
    -0.88
    Ö¼
    -0.84
    tle
    -0.83
    reads
    -0.80
    âĶģ
    -0.78
    orian
    -0.77
    gets
    -0.77
    heimer
    -0.77
    ql
    -0.77
    places
    -0.76
    POSITIVE LOGITS
     helicopters
    1.17
     helicopter
    1.14
     hangar
    0.95
     helic
    0.94
     Helic
    0.94
     parach
    0.92
     blades
    0.89
     hovering
    0.89
     helicop
    0.88
     skiing
    0.88
    Activations Density 0.010%

    No Known Activations