© 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. 2-RES-JB
    11. 1508
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns related to geopolitical events

    oai_token-act-pair · gpt-3.5-turbo

    names of specific locations and communities, particularly in the context of conflict and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĢº
    -0.60
     ..........
    -0.58
    âķIJâķIJ
    -0.54
    ----
    -0.52
    nos
    -0.52
    taboola
    -0.50
    -0.50
     Morty
    -0.50
    âĢİ
    -0.48
    ++++++++++++++++
    -0.48
    POSITIVE LOGITS
    schild
    0.48
     muse
    0.46
     semblance
    0.44
    unia
    0.44
    agine
    0.44
     Citadel
    0.44
    anasia
    0.43
     genesis
    0.43
    owan
    0.42
    ensibly
    0.42
    Activations Density 1.617%

    No Known Activations