© 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. 15827
    Prev
    Next
    INDEX
    Explanations

    phrases related to definitions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to production and economic systems

    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
     Vaugh
    -0.57
     ensuing
    -0.53
     tallied
    -0.47
    çīĪ
    -0.46
     headline
    -0.45
     outing
    -0.44
     Baird
    -0.44
     ensued
    -0.44
     rollout
    -0.44
     lawmaker
    -0.42
    POSITIVE LOGITS
     alot
    0.70
     âĢº
    0.66
     ..........
    0.65
    DragonMagazine
    0.58
    Very
    0.53
    ↵Âł
    0.52
    abetic
    0.52
    âĢ¦âĢ¦âĢ¦âĢ¦
    0.51
    ¶
    0.51
     à¤
    0.51
    Activations Density 1.445%

    No Known Activations