© 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. 20315
    Prev
    Next
    INDEX
    Explanations

    phrases related to explanations or statements given by someone

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to explanations or clarifications

    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
    folk
    -0.67
    alysed
    -0.66
    mt
    -0.66
    ãĥİ
    -0.66
    pmwiki
    -0.65
    ija
    -0.64
    Untitled
    -0.64
    emort
    -0.62
     Written
    -0.62
    FIL
    -0.62
    POSITIVE LOGITS
     that
    0.88
     sarcast
    0.82
     noting
    0.80
     himself
    0.79
     furthermore
    0.77
     stressing
    0.76
     rhet
    0.74
     emphasizing
    0.73
     bluntly
    0.73
     listeners
    0.69
    Activations Density 0.235%

    No Known Activations