© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23948
    Prev
    Next
    INDEX
    Explanations

    mentions of helicopters

    oai_token-act-pair · gpt-3.5-turbo

    instances of helicopters mentioned in various contexts

    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
    furt
    -1.01
    tle
    -0.92
    reads
    -0.87
    Detailed
    -0.87
    tg
    -0.79
    abet
    -0.79
    orian
    -0.77
    gets
    -0.77
    heimer
    -0.75
    ª
    -0.75
    POSITIVE LOGITS
     helicopter
    1.30
     helicopters
    1.28
     Helic
    1.08
     parach
    1.05
     helic
    1.04
     hangar
    0.98
     helicop
    0.96
     jets
    0.93
     parachute
    0.93
     skiing
    0.92
    Activations Density 0.017%

    No Known Activations