© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6438
    Prev
    Next
    INDEX
    Explanations

    programming code snippets containing comments or explanations related to code functionalities

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
     withd
    -0.91
     grounding
    -0.80
     glim
    -0.73
     granddaughter
    -0.73
     challeng
    -0.70
     enthusi
    -0.67
     prototyp
    -0.66
     Frenchman
    -0.66
     grandson
    -0.66
     disadvant
    -0.65
    POSITIVE LOGITS
    jpg
    1.34
    htm
    1.30
    txt
    1.28
    html
    1.28
    php
    1.22
    com
    1.22
    png
    1.19
    exe
    1.18
    tumblr
    1.17
    blogspot
    1.17
    Activations Density 0.136%

    No Known Activations