Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20984
    Prev
    Next
    INDEX
    Explanations

    Twitter handles or hashtags

    oai_token-act-pair · gpt-3.5-turbo

    references to Twitter 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
     Shack
    -0.74
     Dahl
    -0.72
     Sphere
    -0.72
     Suff
    -0.70
     Duff
    -0.68
     Ballard
    -0.65
     Ruth
    -0.65
     Aberdeen
    -0.65
     Forth
    -0.63
     Wonderland
    -0.63
    POSITIVE LOGITS
    twitter
    1.04
    ileaks
    0.85
    sonian
    0.79
    feed
    0.75
    username
    0.74
    ipe
    0.74
    @@@@@@@@
    0.74
    facebook
    0.74
    /#
    0.73
    storms
    0.71
    Activations Density 0.010%

    No Known Activations