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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 22362
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical turning around or changing direction in a literal or metaphorical sense

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to change in direction or orientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.80
     confir
    -0.65
    inks
    -0.64
    lain
    -0.64
     ceilings
    -0.64
    egg
    -0.63
     epid
    -0.62
    cliffe
    -0.61
     indemn
    -0.60
     breached
    -0.60
    POSITIVE LOGITS
     âĸº
    0.68
    wagen
    0.67
    isance
    0.66
     tide
    0.63
     deaf
    0.63
    ï¸
    0.63
     Pace
    0.62
    iris
    0.61
     repentance
    0.61
    ħ
    0.61
    Activations Density 0.088%

    No Known Activations