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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 19460
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences such as codes or references

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols often used in technical or scientific contexts

    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
     Seym
    -0.76
     lipstick
    -0.69
    ebin
    -0.69
     stump
    -0.68
     mockery
    -0.67
     puff
    -0.66
     floppy
    -0.66
     Winc
    -0.66
    ilan
    -0.65
    rish
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.09
    âĶĢâĶĢ
    0.89
    ï¸
    0.86
    âĢł
    0.85
    STEM
    0.85
    âģ
    0.84
    ··
    0.83
    âĶĢâĶĢâĶĢâĶĢ
    0.82
    ¶
    0.81
    ±
    0.81
    Activations Density 0.572%

    No Known Activations