© 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. 6-RES-JB
    11. 958
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps

    oai_token-act-pair · gpt-3.5-turbo

    negative symbols and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accus
    -0.67
     voic
    -0.62
    oran
    -0.61
     intimidate
    -0.60
    lly
    -0.60
     grop
    -0.60
     interrupted
    -0.60
     outl
    -0.60
    esan
    -0.59
    anwhile
    -0.58
    POSITIVE LOGITS
    15
    1.06
    09
    1.06
    08
    1.05
    01
    1.03
    05
    1.03
    2018
    1.02
    14
    1.02
    16
    1.01
    13
    0.99
    17
    0.99
    Activations Density 0.043%

    No Known Activations