© 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. 7275
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing high value or importance

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that emphasize qualities of significance and rarity

    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
    eller
    -0.69
     Houses
    -0.66
    ²¾
    -0.64
    ecast
    -0.63
    geist
    -0.62
    house
    -0.62
    eanor
    -0.61
    aign
    -0.61
    chn
    -0.61
    elist
    -0.60
    POSITIVE LOGITS
    iqueness
    0.84
     Tup
    0.76
     unbeat
    0.72
     Mehran
    0.70
    âĺħâĺħ
    0.70
     Jagu
    0.67
    cffffcc
    0.66
     amaz
    0.65
    BILITIES
    0.65
     irresistible
    0.65
    Activations Density 0.027%

    No Known Activations