© 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. 3-RES-JB
    6. 15711
    Prev
    Next
    INDEX
    Explanations

    hashtags or phrases starting with hashtags

    oai_token-act-pair · gpt-3.5-turbo

    references to hashtags used in social media discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trave
    -0.73
    undai
    -0.70
     oun
    -0.70
    opathic
    -0.68
    ramid
    -0.67
     contracting
    -0.66
    secut
    -0.66
    artment
    -0.64
    nih
    -0.64
     trib
    -0.63
    POSITIVE LOGITS
     hashtag
    1.31
    ="#
    1.09
     hasht
    1.06
    tags
    0.92
    =""
    0.88
    âĢİ
    0.87
     "#
    0.86
    =\"
    0.79
     (#
    0.77
    SHARE
    0.75
    Activations Density 0.006%

    No Known Activations