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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14410
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures, particularly in the context of fermentation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific fields of science or disciplines ending in 'omy' or 'ogy'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posted
    -0.68
    ivism
    -0.67
    itarian
    -0.66
    ileaks
    -0.66
    rising
    -0.66
    leased
    -0.65
    ividual
    -0.65
    ivist
    -0.64
    izen
    -0.64
    ipeg
    -0.64
    POSITIVE LOGITS
    gdala
    1.15
    omy
    1.00
    elia
    0.83
     Brus
    0.83
    cn
    0.74
    opathy
    0.73
    ctor
    0.72
    opathic
    0.70
    ller
    0.69
    ophy
    0.68
    Activations Density 0.015%

    No Known Activations