© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 7665
    Prev
    Next
    INDEX
    Explanations

    mentions of objects made of material due to being constructed using a specific sheet

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of sheets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qua
    -0.80
     Valley
    -0.66
    Ben
    -0.62
    Sax
    -0.61
    Interstitial
    -0.60
    oise
    -0.59
    olulu
    -0.59
    CEPT
    -0.58
     sensitivity
    -0.58
     unin
    -0.58
    POSITIVE LOGITS
    sheet
    1.65
     sheet
    1.41
    sheets
    1.40
     sheets
    1.22
     Sheet
    1.09
    heet
    0.97
    enium
    0.81
     spreadsheet
    0.77
    hematically
    0.77
    chart
    0.73
    Activations Density 0.014%

    No Known Activations