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. 7-RES-JB
    6. 22512
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific entities or brands

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places, organizations, and entertainment references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )=(
    -0.72
    ¶ħ
    -0.68
    hement
    -0.68
    anwhile
    -0.67
    mble
    -0.60
    assetsadobe
    -0.59
    ,,,,
    -0.59
     ..........
    -0.59
     unloaded
    -0.58
     headlights
    -0.57
    POSITIVE LOGITS
     Continent
    0.65
    Fest
    0.63
     Eden
    0.63
     Era
    0.62
    verse
    0.61
    Wiki
    0.61
    opia
    0.60
     Island
    0.60
     experien
    0.60
    $.
    0.59
    Activations Density 0.852%

    No Known Activations