© 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. 3-RES-JB
    11. 14769
    Prev
    Next
    INDEX
    Explanations

    phrases related to whistleblowing or alerting others to issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whistle" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arya
    -0.75
    ivia
    -0.74
    itating
    -0.70
    ivan
    -0.70
    ggles
    -0.69
    itals
    -0.68
    erker
    -0.65
    oult
    -0.64
    Interstitial
    -0.63
    illard
    -0.62
    POSITIVE LOGITS
     whistle
    1.11
    dropping
    0.83
    keeper
    0.81
    backs
    0.78
     whist
    0.73
    ãĤ©
    0.71
    glers
    0.70
    ãĥ£
    0.69
    bler
    0.69
    grass
    0.69
    Activations Density 0.006%

    No Known Activations