© 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. 18648
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to opinions or quotes being expressed

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols and repetitive phrases indicating administrative or bureaucratic statements

    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
    chnology
    -0.75
    atown
    -0.65
    osite
    -0.64
    ifice
    -0.63
     Marketable
    -0.60
     handy
    -0.59
    icy
    -0.59
     disguise
    -0.59
     shorth
    -0.59
    chieve
    -0.58
    POSITIVE LOGITS
    said
    1.59
     said
    1.16
    according
    1.05
     says
    1.03
     according
    0.95
     explained
    0.93
     explains
    0.88
    she
    0.87
     commented
    0.85
     argues
    0.84
    Activations Density 0.142%

    No Known Activations