© 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. 11-RES-JB
    11. 10182
    Prev
    Next
    INDEX
    Explanations

    large numbers related to people or populations

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to large groups of people or metrics associated with population statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reminding
    -0.71
    Recomm
    -0.67
     Saying
    -0.63
    ãĤ¦ãĤ¹
    -0.60
    hib
    -0.58
    ãĥĥ
    -0.58
     Quote
    -0.57
    cknow
    -0.57
     nicely
    -0.57
    #$
    -0.56
    POSITIVE LOGITS
     perished
    1.28
     reside
    1.26
     died
    1.20
     participated
    1.20
     resided
    1.09
     have
    1.09
     were
    1.08
     remain
    1.08
     comprise
    1.04
     are
    1.04
    Activations Density 0.217%

    No Known Activations