© 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. 9299
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases related to position

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize transitions or moments in time

    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
    owered
    -0.73
    mouth
    -0.69
    olls
    -0.69
     polled
    -0.64
    arov
    -0.63
    emouth
    -0.60
    arte
    -0.60
    aston
    -0.60
    ocrat
    -0.58
    mson
    -0.58
    POSITIVE LOGITS
     later
    1.23
     hereafter
    0.98
     detail
    0.94
     shortly
    0.93
     tomorrow
    0.93
     below
    0.93
     Later
    0.89
     momentarily
    0.88
    later
    0.88
    Chapter
    0.85
    Activations Density 0.238%

    No Known Activations