© 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. 7-RES-JB
    11. 13450
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Again" followed by a comma along with related content

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express repetition or ongoing action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rt
    -0.68
    adena
    -0.68
    kees
    -0.67
    ufact
    -0.65
    leton
    -0.65
    etheless
    -0.65
    intestinal
    -0.61
    othal
    -0.59
    anners
    -0.59
    retty
    -0.59
    POSITIVE LOGITS
     emphasis
    0.80
     caveat
    0.78
     note
    0.67
     emph
    0.66
    acus
    0.63
     anecdotal
    0.63
     reiter
    0.63
     caveats
    0.62
     unanswered
    0.62
     reference
    0.62
    Activations Density 0.107%

    No Known Activations