© 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. 10-RES-JB
    11. 12115
    Prev
    Next
    INDEX
    Explanations

    places or objects that are physically close

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kay
    -0.76
    olars
    -0.66
    anners
    -0.64
    krit
    -0.58
    adel
    -0.58
    cn
    -0.58
    imar
    -0.58
    ampions
    -0.57
    inger
    -0.57
    azeera
    -0.56
    POSITIVE LOGITS
     door
    1.32
     Door
    0.98
    door
    0.96
     to
    0.89
     thereto
    0.72
     doors
    0.71
     aisle
    0.71
     drawer
    0.69
    to
    0.66
     doorway
    0.66
    Activations Density 0.019%

    No Known Activations