© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 20575
    Prev
    Next
    INDEX
    Explanations

    adjectives emphasizing intensity, such as "real", "good", "quickly", "young", "high", and "low"

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing conditions or qualities in a variety of contexts

    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
    CHAT
    -0.65
    EE
    -0.63
    CTV
    -0.62
     Maze
    -0.60
    ee
    -0.60
    bright
    -0.59
     SUP
    -0.59
    zh
    -0.58
    SUP
    -0.58
    onto
    -0.57
    POSITIVE LOGITS
     (>
    0.81
    ractive
    0.63
     Thing
    0.63
    omical
    0.62
    Ö
    0.61
    士
    0.60
     odds
    0.60
     (~
    0.59
     resume
    0.59
    retch
    0.58
    Activations Density 0.261%

    No Known Activations