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. 8-RES-JB
    6. 16064
    Prev
    Next
    INDEX
    Explanations

    months or seasons mentioned in a temporal context, such as 'spring', 'summer', 'fall', or 'month'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods, particularly related to seasons and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     textual
    -0.78
     cumbers
    -0.71
     sync
    -0.70
     gib
    -0.69
     regression
    -0.68
    verages
    -0.67
    idine
    -0.65
    erate
    -0.65
     bom
    -0.64
     continuity
    -0.63
    POSITIVE LOGITS
     announcing
    0.72
    flower
    0.70
    furt
    0.70
    tower
    0.66
    obyl
    0.66
    ifer
    0.66
     Giul
    0.65
     Harbor
    0.65
    ghan
    0.65
    angel
    0.63
    Activations Density 0.098%

    No Known Activations