© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 593
    Prev
    Next
    INDEX
    Explanations

    the word "Perhaps" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce hypothetical situations or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     operation
    -0.76
     live
    -0.74
     super
    -0.68
     approved
    -0.68
     every
    -0.65
     process
    -0.64
     side
    -0.64
     sides
    -0.63
     following
    -0.63
     code
    -0.62
    POSITIVE LOGITS
     Perhaps
    2.77
    Perhaps
    2.56
    perhaps
    2.11
     Surely
    1.79
    Maybe
    1.73
     Presumably
    1.70
     Possibly
    1.68
     Certainly
    1.68
     Maybe
    1.66
     perhaps
    1.50
    Activations Density 0.018%

    No Known Activations