© 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. 0-RES-JB
    11. 4165
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking up physical space or physical presence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of occupation or filling a space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggles
    -0.75
    ecycle
    -0.67
    eways
    -0.67
    rone
    -0.65
    atari
    -0.64
    ourses
    -0.64
    iscovery
    -0.63
    yssey
    -0.62
     lift
    -0.62
    eport
    -0.62
    POSITIVE LOGITS
     possessing
    2.21
     lacking
    2.16
     occupying
    2.11
     residing
    1.70
     owning
    1.62
     comprising
    1.51
     exhibiting
    1.46
     weighing
    1.46
     needing
    1.45
     employing
    1.45
    Activations Density 0.034%

    No Known Activations