© 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. 20257
    Prev
    Next
    INDEX
    Explanations

    facts or statistics that are contrasted with a "but" in the sentence

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that are completely empty or devoid of content

    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
    tnc
    -0.86
    edu
    -0.76
    onica
    -0.71
    ict
    -0.69
    umat
    -0.68
    uto
    -0.68
    obyl
    -0.67
    iw
    -0.67
    代
    -0.66
    oire
    -0.65
    POSITIVE LOGITS
     nevertheless
    1.18
     nonetheless
    1.13
     retains
    1.08
     luckily
    1.04
     alas
    1.04
     lacks
    1.04
     prefers
    1.02
     fortunately
    1.01
     lacked
    0.99
     insists
    0.98
    Activations Density 0.157%

    No Known Activations