Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22779
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or different aspects of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of multiple interpretations or perspectives on a topic

    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
    bart
    -0.66
    tailed
    -0.63
    andel
    -0.62
    alsa
    -0.61
    ctors
    -0.61
    perty
    -0.61
    prus
    -0.60
    lish
    -0.60
    multiple
    -0.59
    mins
    -0.59
    POSITIVE LOGITS
     resembles
    0.75
     analogous
    0.72
     resembling
    0.71
    ,
    0.68
     reminiscent
    0.68
     resemble
    0.67
     mirror
    0.64
     embodies
    0.64
     it
    0.63
     this
    0.61
    Activations Density 0.088%

    No Known Activations