© 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. 1903
    Prev
    Next
    INDEX
    Explanations

    words related to transitional states or periods

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transitional phases or states

    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
     Tuls
    -0.84
    lot
    -0.76
    agi
    -0.74
     Bezos
    -0.71
     Crunch
    -0.71
     Dow
    -0.70
    rigan
    -0.69
     Crush
    -0.69
     VIDEOS
    -0.68
    abeth
    -0.67
    POSITIVE LOGITS
     transitional
    3.10
    itional
    1.89
     intermediate
    1.41
     primitive
    1.36
     embryonic
    1.15
     intermedi
    1.15
     squat
    1.08
     elusive
    1.06
     intermediary
    1.05
     nascent
    1.03
    Activations Density 0.071%

    No Known Activations