© 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. 4-RES-JB
    11. 4109
    Prev
    Next
    INDEX
    Explanations

    URLs starting with 'https'

    oai_token-act-pair · gpt-3.5-turbo

    web addresses and URLs

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

    No Comments

    Negative Logits
     Morse
    -0.80
    ãĥ¼ãĥĨ
    -0.71
    gdala
    -0.71
     Takeru
    -0.69
     deceive
    -0.69
     sided
    -0.69
     Labrador
    -0.68
     Pigs
    -0.67
    anwhile
    -0.67
     Arri
    -0.67
    POSITIVE LOGITS
    www
    1.46
    twitter
    1.24
    natureconservancy
    1.23
    ://
    1.22
    github
    1.13
    docs
    1.06
    doi
    1.02
    youtu
    0.98
    :/
    0.88
    encrypted
    0.87
    Activations Density 0.009%

    No Known Activations