© 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. 22635
    Prev
    Next
    INDEX
    Explanations

    punctuation marks preceding clauses or sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Now."

    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
    SourceFile
    -1.03
    è¦ļéĨĴ
    -0.88
    VERTISEMENT
    -0.84
    MpServer
    -0.83
    ļéĨĴ
    -0.71
    conom
    -0.69
    ahan
    -0.67
    oslav
    -0.65
    MSN
    -0.64
    ãĤ¦ãĤ¹
    -0.62
    POSITIVE LOGITS
     however
    1.11
     alas
    0.97
    adays
    0.96
     moreover
    0.90
     according
    0.88
     though
    0.86
     thankfully
    0.85
     somew
    0.84
     despite
    0.84
     although
    0.81
    Activations Density 0.105%

    No Known Activations