© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 23515
    Prev
    Next
    INDEX
    Explanations

    random characters and gibberish in the text data

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols in various encodings, indicating a focus on non-standard textual elements

    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
     vacuum
    -0.79
    oresc
    -0.74
     fluorescent
    -0.74
     turbines
    -0.73
     pitches
    -0.72
     Frankenstein
    -0.71
     robotic
    -0.70
     roller
    -0.70
     stunts
    -0.70
     relegation
    -0.69
    POSITIVE LOGITS
     Allaah
    1.31
    á¸
    1.15
     Ibn
    1.13
     Apostle
    1.04
     Quran
    1.04
    Sah
    1.00
    hari
    1.00
    Allah
    1.00
    iyah
    0.99
     ibn
    0.99
    Activations Density 0.142%

    No Known Activations