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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17431
    Prev
    Next
    INDEX
    Explanations

    hash tags

    oai_token-act-pair · gpt-3.5-turbo

    references to hashtags used in social media discussions

    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
    ramid
    -0.73
    kus
    -0.73
     oun
    -0.73
    ntil
    -0.69
    ateral
    -0.69
    undai
    -0.68
     trave
    -0.65
    artment
    -0.65
     contracting
    -0.65
     chambers
    -0.65
    POSITIVE LOGITS
     hashtag
    1.26
     hasht
    1.04
     "#
    0.98
    ="#
    0.97
    tags
    0.97
    =""
    0.89
    âĢİ
    0.86
    =\"
    0.85
    netflix
    0.78
     (#
    0.73
    Activations Density 0.011%

    No Known Activations