© 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. 10-RES-JB
    11. 14007
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing a quantity or amount

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    months
    -0.62
     livest
    -0.61
    TOP
    -0.61
    ynes
    -0.60
     cleaners
    -0.60
    overe
    -0.59
    alez
    -0.58
     withd
    -0.58
    etts
    -0.56
    fters
    -0.56
    POSITIVE LOGITS
     course
    0.82
    erous
    0.80
     them
    0.75
    course
    0.74
     yours
    0.69
     ours
    0.69
     theirs
    0.66
    Sense
    0.66
     us
    0.65
     those
    0.64
    Activations Density 0.061%

    No Known Activations