© 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. 11-RES-JB
    11. 9862
    Prev
    Next
    INDEX
    Explanations

    the word "avatar."

    oai_token-act-pair · gpt-3.5-turbo

    references to names or terms related to sports and athletes

    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
     worth
    -0.70
     welfare
    -0.62
     typed
    -0.60
     please
    -0.59
     clim
    -0.59
     changing
    -0.58
     displacement
    -0.57
     nudity
    -0.57
     CLSID
    -0.56
     manual
    -0.56
    POSITIVE LOGITS
    enture
    1.29
    irus
    1.19
    ilion
    1.18
    irtual
    1.14
    ocado
    1.14
    antage
    1.11
    ril
    1.10
    iolet
    1.09
    sky
    1.09
    ishly
    1.09
    Activations Density 0.041%

    No Known Activations