© 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. 2-RES-JB
    11. 23951
    Prev
    Next
    INDEX
    Explanations

    words related to actions involving stealth or secrecy, especially when the action involves movement

    oai_token-act-pair · gpt-3.5-turbo

    references to sneezing and variations of the word "sneeze."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    66666666
    -0.76
     GOODMAN
    -0.76
    FORM
    -0.74
    ãĥĩ
    -0.69
     chronological
    -0.61
    phabet
    -0.61
    HCR
    -0.61
     Morse
    -0.60
    onial
    -0.60
     Dispatch
    -0.59
    POSITIVE LOGITS
     sne
    1.12
     Sne
    0.82
    aks
    0.81
    ez
    0.77
    fters
    0.77
    aker
    0.76
    pe
    0.76
    aky
    0.76
    itched
    0.75
    inton
    0.75
    Activations Density 0.006%

    No Known Activations