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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 3390
    Prev
    Next
    INDEX
    Explanations

    mentions of cherries and items associated with cherries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "cherry" and related phrases

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

    No Comments

    Negative Logits
    atern
    -0.88
    ahime
    -0.85
    RAW
    -0.80
    entric
    -0.79
    orough
    -0.78
    afety
    -0.77
    Interstitial
    -0.76
    ear
    -0.76
    ASC
    -0.75
    oppable
    -0.73
    POSITIVE LOGITS
     cherry
    1.22
     bloss
    1.15
     Blossom
    1.13
     tomatoes
    0.93
     MX
    0.92
     Cherry
    0.85
     juice
    0.83
     tomato
    0.82
     flavored
    0.82
     pie
    0.81
    Activations Density 0.010%

    No Known Activations