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. 4-RES-JB
    6. 12644
    Prev
    Next
    INDEX
    Explanations

    references to last-minute actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to time, particularly focusing on last-minute or urgent actions

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

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.80
    Bir
    -0.71
    Hor
    -0.69
    ashtra
    -0.68
    origin
    -0.66
     Bir
    -0.65
    WD
    -0.65
    RW
    -0.63
    atri
    -0.63
    sbm
    -0.62
    POSITIVE LOGITS
    imester
    0.87
    cation
    0.79
    lihood
    0.78
    endment
    0.76
    eme
    0.75
     obscurity
    0.73
     innocence
    0.73
    theless
    0.71
     voic
    0.69
    liest
    0.65
    Activations Density 0.073%

    No Known Activations