© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14894
    Prev
    Next
    INDEX
    Explanations

    terms related to legal, regulatory, or policy matters

    oai_token-act-pair · gpt-3.5-turbo

    legal and regulatory terms related to rights and actions

    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
    Ïī
    -0.65
    APE
    -0.62
    TYPE
    -0.62
    RE
    -0.61
    èª
    -0.61
    é¾į
    -0.61
    INST
    -0.60
    ãĤ¹ãĥĪ
    -0.60
     theirs
    -0.60
    è»
    -0.60
    POSITIVE LOGITS
    ource
    1.08
    hift
    1.07
    afety
    0.98
    ugar
    0.96
    pite
    0.95
    ourcing
    0.95
    hops
    0.95
    uggest
    0.95
    cript
    0.93
    lash
    0.93
    Activations Density 0.139%

    No Known Activations