© 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 EvalsExportsinterp-engineNEWAPI 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. 11690
    Prev
    Next
    INDEX
    Explanations

    phrases with numbered organizational structures

    oai_token-act-pair · gpt-3.5-turbo

    structures that present multiple points or reasons

    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
    orian
    -0.77
    urated
    -0.73
     lett
    -0.70
    orate
    -0.70
    stra
    -0.66
    acan
    -0.64
    ãĤĭ
    -0.61
    rams
    -0.60
    kers
    -0.60
     overtime
    -0.59
    POSITIVE LOGITS
     Firstly
    1.65
    Firstly
    1.61
     First
    1.41
    First
    1.38
     first
    1.20
    1
    1.19
    first
    1.10
     FIRST
    0.99
     1
    0.91
     starters
    0.89
    Activations Density 0.627%

    No Known Activations