© 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. 11745
    Prev
    Next
    INDEX
    Explanations

    references to the beginning or start of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "opening" in various contexts

    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
    tics
    -0.90
    cia
    -0.88
    ieving
    -0.87
    zin
    -0.77
    lean
    -0.75
    rome
    -0.73
    mel
    -0.71
    ka
    -0.71
    cles
    -0.69
    ided
    -0.69
    POSITIVE LOGITS
     ceremonies
    0.84
     Doors
    0.82
     opening
    0.82
     doors
    0.80
     salv
    0.75
     openings
    0.75
     weekend
    0.75
     reopen
    0.73
     Weekend
    0.73
     ceremony
    0.73
    Activations Density 0.022%

    No Known Activations