© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9098
    Prev
    Next
    INDEX
    Explanations

    prepositions and directional words related to camera positions and movement

    oai_token-act-pair · gpt-3.5-turbo

    references to positioning and direction towards specific objects or targets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.77
    ury
    -0.76
    uits
    -0.74
    Ĥª
    -0.72
    WAYS
    -0.71
    ulations
    -0.71
    Quantity
    -0.69
    vere
    -0.66
    eson
    -0.66
    uci
    -0.65
    POSITIVE LOGITS
     target
    1.30
     destination
    1.25
     nearest
    1.22
     center
    1.15
     horizon
    1.12
     edge
    1.09
     source
    1.08
     ceiling
    1.07
     periphery
    1.06
     camera
    1.06
    Activations Density 0.221%

    No Known Activations