© 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. 1923
    Prev
    Next
    INDEX
    Explanations

    instances where something narrowly prevented a negative event from occurring

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "narrowly."

    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
     Maid
    -0.73
     Apostles
    -0.70
     Occupations
    -0.70
     Founding
    -0.69
     Parade
    -0.67
     River
    -0.67
     Cth
    -0.65
     Viking
    -0.65
     Continent
    -0.65
     Golem
    -0.65
    POSITIVE LOGITS
     narrowly
    1.11
     minded
    0.92
     aver
    0.86
    Ń·
    0.80
    velength
    0.79
     tailored
    0.78
     exempted
    0.74
    quer
    0.74
    iciary
    0.73
     avoided
    0.72
    Activations Density 0.002%

    No Known Activations