© 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. 6-RES-JB
    11. 1716
    Prev
    Next
    INDEX
    Explanations

    phrases indicating coincidence or circumstance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "happens to be" or similar constructions indicating a state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sett
    -0.82
    Reviewed
    -0.74
    ipers
    -0.70
    anooga
    -0.69
     canopy
    -0.66
    allo
    -0.64
    beard
    -0.64
    MAP
    -0.63
    yre
    -0.63
    DOS
    -0.63
    POSITIVE LOGITS
     coincide
    1.06
     belong
    0.77
     resemble
    0.76
     specialize
    0.74
     introduce
    0.73
     stumble
    0.73
     dispose
    0.72
     mention
    0.70
     haunt
    0.68
    PsyNetMessage
    0.67
    Activations Density 0.045%

    No Known Activations