© 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. 9-RES-JB
    11. 3635
    Prev
    Next
    INDEX
    Explanations

    phrases related to emergency situations and response

    oai_token-act-pair · gpt-3.5-turbo

    instances of emergency situations involving aviation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MSN
    -0.54
     unfocusedRange
    -0.53
    estern
    -0.51
    Ô
    -0.49
     google
    -0.48
     Hawks
    -0.48
     Gem
    -0.46
     Youtube
    -0.46
     Neo
    -0.44
    MET
    -0.44
    POSITIVE LOGITS
    *.
    1.00
    .[
    0.91
    .?
    0.91
    .''.
    0.86
     lest
    0.85
    .*
    0.84
    .
    0.80
    .�
    0.75
    .).
    0.75
    ãĢĤ
    0.75
    Activations Density 1.057%

    No Known Activations