© 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. 23910
    Prev
    Next
    INDEX
    Explanations

    references to future events or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the future and its implications

    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
    »Ĵ
    -0.77
    inese
    -0.67
    pired
    -0.66
    istor
    -0.64
    joice
    -0.63
    ghan
    -0.63
    ishable
    -0.62
    adobe
    -0.62
    ilant
    -0.62
    gger
    -0.62
    POSITIVE LOGITS
     participation
    1.22
     availability
    1.19
     involvement
    1.17
     usage
    1.16
     visibility
    1.16
     behavior
    1.13
     reliability
    1.11
    ness
    1.09
     accessibility
    1.09
     connectivity
    1.09
    Activations Density 0.687%

    No Known Activations