© 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. 16861
    Prev
    Next
    INDEX
    Explanations

    words related to chimneys

    oai_token-act-pair · gpt-3.5-turbo

    references to chimneys and related concepts

    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
    ulf
    -0.77
    etime
    -0.70
    olic
    -0.67
    obile
    -0.66
    idas
    -0.65
    essional
    -0.65
    ana
    -0.65
    oint
    -0.64
     Bere
    -0.63
     2018
    -0.63
    POSITIVE LOGITS
     chim
    4.29
     Chim
    2.71
     chimpanzees
    1.85
     chimpan
    1.66
     pip
    1.35
     apes
    1.17
     Neander
    1.13
     gor
    1.05
     Chimera
    1.04
     cis
    1.00
    Activations Density 0.020%

    No Known Activations