© 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. 10-RES-JB
    11. 6755
    Prev
    Next
    INDEX
    Explanations

    quotations or statements attributed to people

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to quotes and statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olit
    -0.60
    hetics
    -0.59
     combined
    -0.59
    together
    -0.59
    utory
    -0.57
    hang
    -0.57
    ouched
    -0.57
     Lots
    -0.56
    Visit
    -0.56
    vable
    -0.56
    POSITIVE LOGITS
     saying
    1.70
     Saying
    1.28
     stating
    1.21
     telling
    1.19
     remark
    1.16
     SAY
    1.14
     noting
    1.01
     estimating
    1.01
     describing
    1.00
     complaining
    0.99
    Activations Density 0.096%

    No Known Activations