© 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. 3-RES-JB
    11. 14768
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases with a strong concluding punctuation

    oai_token-act-pair · gpt-3.5-turbo

    punctuated sentences or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emaker
    -0.74
    iber
    -0.73
     tack
    -0.71
     purse
    -0.71
     quir
    -0.70
    thal
    -0.68
     disemb
    -0.67
     mosqu
    -0.67
     pit
    -0.66
     clutch
    -0.66
    POSITIVE LOGITS
     However
    1.20
     Though
    1.11
     Although
    1.07
     Regardless
    1.05
     Therefore
    1.05
     Besides
    1.04
     Whether
    1.04
     Especially
    1.04
     Nevertheless
    1.03
     While
    1.02
    Activations Density 1.493%

    No Known Activations