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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 20039
    Prev
    Next
    INDEX
    Explanations

    mentions of airplane crashes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "plane" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laus
    -0.92
    FINE
    -0.78
    PUT
    -0.76
    essee
    -0.72
     Cumber
    -0.71
    shire
    -0.70
    UGC
    -0.68
    uces
    -0.67
    lishes
    -0.67
    optional
    -0.66
    POSITIVE LOGITS
    walk
    1.09
     airliner
    1.03
    walker
    0.98
     prope
    0.98
     plane
    0.97
     airplanes
    0.97
     hangar
    0.96
     wreckage
    0.94
    plane
    0.93
     planes
    0.93
    Activations Density 0.020%

    No Known Activations