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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12455
    Prev
    Next
    INDEX
    Explanations

    verbs denoting lifting or being uplifted

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with buoyancy and elevation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thia
    -0.73
    pres
    -0.65
     TEXT
    -0.63
    thus
    -0.61
    ulhu
    -0.61
    how
    -0.60
     Heck
    -0.60
    FE
    -0.60
    pace
    -0.59
     millennium
    -0.59
    POSITIVE LOGITS
     buoy
    1.33
    ancy
    1.00
     gust
    0.98
    glomer
    0.86
    ishers
    0.84
    ishment
    0.83
     earthqu
    0.80
     helium
    0.75
    raints
    0.75
    rehend
    0.75
    Activations Density 0.009%

    No Known Activations