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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 8325
    Prev
    Next
    INDEX
    Explanations

    dates and deadlines mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of deadlines and time frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.84
    cipl
    -0.71
    tw
    -0.71
    deck
    -0.70
    olulu
    -0.70
    thora
    -0.70
    wagen
    -0.69
    tek
    -0.69
    shield
    -0.68
    ply
    -0.68
    POSITIVE LOGITS
     completion
    1.12
     onset
    1.06
     arrival
    1.04
     gratification
    0.94
     departure
    0.93
     commencement
    0.91
     clearance
    0.87
     entry
    0.87
     enactment
    0.86
     completing
    0.86
    Activations Density 0.243%

    No Known Activations