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. 7-RES-JB
    6. 10683
    Prev
    Next
    INDEX
    Explanations

    mentions of time, particularly the word "ago."

    oai_token-act-pair · gpt-3.5-turbo

    references to the time frame of "a week ago" or similar past durations

    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
    eers
    -0.77
    nce
    -0.73
    eq
    -0.72
    amins
    -0.66
    DOS
    -0.63
     chromosome
    -0.62
     Roose
    -0.61
    atin
    -0.60
     Bastard
    -0.60
    eer
    -0.60
    POSITIVE LOGITS
    opausal
    0.84
    èª
    0.79
    rolet
    0.69
     when
    0.67
     afternoon
    0.65
    ividual
    0.62
    aido
    0.62
    obyl
    0.62
     retracted
    0.61
    iversary
    0.61
    Activations Density 0.022%

    No Known Activations