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. 3-RES-JB
    6. 19007
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'ailing' or 'ceiling'

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or participles ending in 'iling'

    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
    axter
    -0.84
    yssey
    -0.75
    orer
    -0.67
    ľ
    -0.65
    orers
    -0.63
    akening
    -0.62
    essa
    -0.61
    oine
    -0.61
    requisite
    -0.60
    yr
    -0.60
    POSITIVE LOGITS
    ptin
    0.81
    Steam
    0.73
    CLASSIFIED
    0.72
    baugh
    0.70
     Nadu
    0.69
    ionage
    0.68
    untled
    0.66
    imentary
    0.62
    erno
    0.62
    rily
    0.62
    Activations Density 0.008%

    No Known Activations