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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 23312
    Prev
    Next
    INDEX
    Explanations

    proper nouns and phrases related to titles or named entities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "to bed" and related forms indicating a state or condition

    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
    adra
    -0.82
    SPONSORED
    -0.80
    apo
    -0.74
    pta
    -0.73
    feat
    -0.71
    Thor
    -0.69
    TYPE
    -0.68
    ede
    -0.68
    endi
    -0.68
    antage
    -0.67
    POSITIVE LOGITS
     aback
    0.93
     Leader
    0.75
     Victims
    0.70
     Thoughts
    0.69
     Advertisement
    0.67
     By
    0.67
     Loaded
    0.66
     Procedures
    0.66
     Benefits
    0.65
     Tracks
    0.63
    Activations Density 0.104%

    No Known Activations