© 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. 22144
    Prev
    Next
    INDEX
    Explanations

    phrases related to being "out of" a certain place or state

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to being "out of control."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ulhu
    -0.76
     Phi
    -0.75
    Ń·
    -0.72
     Doodle
    -0.69
     Horus
    -0.67
     Illum
    -0.66
     Confederation
    -0.66
     Osiris
    -0.65
     Silk
    -0.62
     Doomsday
    -0.61
    POSITIVE LOGITS
    dated
    1.36
    numbered
    1.23
    of
    1.20
    performing
    1.17
    door
    1.13
    spoken
    1.12
    sized
    1.11
    educated
    1.04
    raised
    1.01
    doors
    1.01
    Activations Density 0.015%

    No Known Activations