Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 16214
    Prev
    Next
    INDEX
    Explanations

    the word "immediately" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "immediately" or related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.71
    midt
    -0.68
     ANGEL
    -0.66
    chance
    -0.65
    mission
    -0.64
    nan
    -0.62
    acus
    -0.62
    features
    -0.62
    ajo
    -0.61
     Vish
    -0.61
    POSITIVE LOGITS
    aneously
    1.17
     thereafter
    0.97
     immediately
    0.89
     followed
    0.84
     preceded
    0.83
     Leilan
    0.83
     afterward
    0.83
    mediately
    0.82
     afterwards
    0.81
    onding
    0.80
    Activations Density 0.012%

    No Known Activations