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

    Neuronpedia

    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. 0-RES-JB
    11. 18332
    Prev
    Next
    INDEX
    Explanations

    references to Apache software

    oai_token-act-pair · gpt-3.5-turbo

    references to the Apache software and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     turnover
    -0.76
    cell
    -0.76
    âĸł
    -0.70
    Cell
    -0.69
     cell
    -0.69
    piece
    -0.67
     dysfunction
    -0.65
    ynes
    -0.63
    cial
    -0.63
     lev
    -0.62
    POSITIVE LOGITS
     Apache
    4.05
    apache
    2.17
     Navajo
    1.43
     Django
    1.38
    Ap
    1.33
     PHP
    1.31
     MySQL
    1.28
    ginx
    1.27
     php
    1.24
     Cherokee
    1.18
    Activations Density 0.025%

    No Known Activations