© 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. 2-RES-JB
    11. 11449
    Prev
    Next
    INDEX
    Explanations

    URLs with the ".php" extension

    oai_token-act-pair · gpt-3.5-turbo

    references to web programming and PHP-related data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Galile
    -0.75
     Intercept
    -0.70
    å°Ĩ
    -0.66
     welf
    -0.65
     ISS
    -0.65
    haul
    -0.65
     tant
    -0.63
     FIGHT
    -0.62
     Yard
    -0.61
     guarded
    -0.59
    POSITIVE LOGITS
    php
    1.24
    qus
    1.23
    ournals
    1.15
    cgi
    1.12
    fw
    0.96
    atform
    0.93
     php
    0.91
    htm
    0.91
    cms
    0.91
    ulhu
    0.91
    Activations Density 0.012%

    No Known Activations