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. 7-RES-JB
    6. 10263
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, specifically mentioning duration since an event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time since an event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dialogue
    -0.71
    Cu
    -0.69
    Si
    -0.69
    STAR
    -0.69
    nels
    -0.68
    gravity
    -0.68
    Jewish
    -0.68
    BUT
    -0.66
    Enh
    -0.65
    Catholic
    -0.65
    POSITIVE LOGITS
    rely
    0.85
     conced
    0.74
     defeat
    0.73
     announcing
    0.71
     completing
    0.70
     retiring
    0.67
    aido
    0.66
     recovering
    0.65
     acclaimed
    0.65
     inception
    0.64
    Activations Density 0.035%

    No Known Activations