© 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. 4-RES-JB
    6. 11166
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms, particularly related to education and technology

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to locations and institutions

    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
     polarized
    -0.49
    :]
    -0.49
     overload
    -0.46
    ":[{"
    -0.46
    ependent
    -0.44
    cipled
    -0.44
     Kafka
    -0.43
    staking
    -0.43
     tremend
    -0.43
     oneself
    -0.43
    POSITIVE LOGITS
    ensis
    0.51
     Jr
    0.49
    ombat
    0.49
    orum
    0.48
    soever
    0.48
    iani
    0.47
    naire
    0.47
    eus
    0.46
    iens
    0.46
    Ore
    0.46
    Activations Density 1.622%

    No Known Activations