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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6663
    Prev
    Next
    INDEX
    Explanations

    time expressions such as months, weeks, and years

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly weeks and months

    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
    Condition
    -0.69
    EStreamFrame
    -0.67
    ãĥĺ
    -0.66
    ãĥİ
    -0.65
    -+
    -0.64
    hop
    -0.62
    depend
    -0.61
    anium
    -0.61
    Probably
    -0.59
     kinda
    -0.59
    POSITIVE LOGITS
     however
    0.85
    ,
    0.81
     meanwhile
    0.80
     HuffPost
    0.74
     Archbishop
    0.67
     alone
    0.66
     Amnesty
    0.66
     rumors
    0.64
     Newsweek
    0.64
    ,.
    0.63
    Activations Density 0.189%

    No Known Activations