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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12795
    Prev
    Next
    INDEX
    Explanations

    phrases related to the status or actions of something or someone

    oai_token-act-pair · gpt-3.5-turbo

    the verb "are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Balt
    -0.76
    Bey
    -0.58
     newcom
    -0.54
    Recomm
    -0.53
    Asset
    -0.52
     behavi
    -0.50
    DEP
    -0.49
    IV
    -0.48
    HUD
    -0.46
    UCT
    -0.46
    POSITIVE LOGITS
     are
    2.17
     aren
    1.85
     ARE
    1.63
    're
    1.59
     were
    1.55
     weren
    1.40
     Are
    1.34
    are
    1.33
    Are
    1.31
    were
    1.30
    Activations Density 0.232%

    No Known Activations