© 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. 8-RES-JB
    11. 1076
    Prev
    Next
    INDEX
    Explanations

    words related to programming and technical issues

    oai_token-act-pair · gpt-3.5-turbo

    specific high-frequency words and phrases related to actions or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dial
    -0.80
     92
    -0.74
     Villa
    -0.70
     91
    -0.68
     Wellington
    -0.68
     Proc
    -0.67
     Mori
    -0.67
     960
    -0.67
     Fritz
    -0.67
     Cult
    -0.66
    POSITIVE LOGITS
    as
    1.51
    asu
    1.23
    AS
    1.19
    asus
    1.13
    ased
    1.08
    asa
    1.05
    asel
    1.04
    asant
    1.00
    asy
    0.98
    asp
    0.98
    Activations Density 0.160%

    No Known Activations