© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 2911
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    elements related to critiques of societal norms and injustices

    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
     Marlins
    -0.53
    dL
    -0.51
    7601
    -0.51
    âķIJâķIJ
    -0.48
     Jindal
    -0.48
    eeper
    -0.47
     Atlantis
    -0.46
    noxious
    -0.45
    versely
    -0.45
    reciation
    -0.44
    POSITIVE LOGITS
    smanship
    0.73
    ãĤ´ãĥ³
    0.61
    ãĥīãĥ©
    0.53
    SpaceEngineers
    0.53
    ãĤ¢ãĥ«
    0.53
    ãĥķãĤ¡
    0.52
     imaginable
    0.51
    ItemImage
    0.51
     outwe
    0.51
    Ore
    0.50
    Activations Density 2.816%

    No Known Activations