© 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. 6464
    Prev
    Next
    INDEX
    Explanations

    ellipses in sentences

    oai_token-act-pair · gpt-3.5-turbo

    ellipses indicating pauses or omissions in communication

    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
    ãĥ¼ãĥĨãĤ£
    -0.95
     purse
    -0.80
    uers
    -0.79
    uous
    -0.72
    ously
    -0.72
     critically
    -0.67
    otine
    -0.67
    gling
    -0.66
     TAMADRA
    -0.65
    uously
    -0.65
    POSITIVE LOGITS
    etc
    1.10
    walking
    0.83
    ordering
    0.82
    where
    0.82
     ..........
    0.80
    orders
    0.80
    essage
    0.79
    quote
    0.79
    ordered
    0.76
    they
    0.75
    Activations Density 0.007%

    No Known Activations