© 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. 20320
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in text

    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
    olves
    -0.71
    aukee
    -0.66
    eers
    -0.63
    nexus
    -0.62
    SourceFile
    -0.61
    è¦ļéĨĴ
    -0.59
    zl
    -0.58
    zing
    -0.57
    igers
    -0.57
    forest
    -0.56
    POSITIVE LOGITS
     although
    0.99
     unlike
    0.98
     contrary
    0.98
     despite
    0.97
     alas
    0.96
     according
    0.89
     barring
    0.88
     somew
    0.87
     notwithstanding
    0.84
     while
    0.84
    Activations Density 0.098%

    No Known Activations