© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2062
    Prev
    Next
    INDEX
    Explanations

    words related to objects and actions in the air

    oai_token-act-pair · gpt-3.5-turbo

    references to flying or airborne elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anan
    -0.73
     Priv
    -0.70
    Ô
    -0.64
     fav
    -0.60
    ¿½
    -0.60
    iago
    -0.59
    compl
    -0.59
    edIn
    -0.59
    ior
    -0.59
    riv
    -0.59
    POSITIVE LOGITS
    waves
    0.98
    walk
    0.79
     canopy
    0.76
     ceiling
    0.75
     somewhere
    0.74
    walker
    0.72
     undet
    0.67
    ousel
    0.66
     continuum
    0.66
     aisle
    0.65
    Activations Density 0.081%

    No Known Activations