© 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. 9-RES-JB
    11. 14135
    Prev
    Next
    INDEX
    Explanations

    specific names or terms starting with "Ab"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character named Ab

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maker
    -0.75
    ancial
    -0.70
     Solitaire
    -0.67
     Disciple
    -0.66
     Titanic
    -0.66
    ä¹ĭ
    -0.64
     Markus
    -0.62
     touches
    -0.60
     Dare
    -0.60
     merit
    -0.58
    POSITIVE LOGITS
    olition
    1.30
    raham
    1.26
    duct
    1.20
    dullah
    1.20
    duction
    1.19
    normal
    1.15
    ortion
    1.12
    rupt
    1.12
    road
    1.12
    addon
    1.11
    Activations Density 0.020%

    No Known Activations