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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 17515
    Prev
    Next
    INDEX
    Explanations

    movie titles, names of people, and years

    oai_token-act-pair · gpt-3.5-turbo

    numbers, dates, and references to noteworthy individuals or events

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

    No Comments

    Negative Logits
    clock
    -0.75
    chery
    -0.65
    cius
    -0.65
     buds
    -0.62
     taped
    -0.61
    ($
    -0.61
     guiActiveUnfocused
    -0.61
    pport
    -0.61
    osis
    -0.61
    media
    -0.60
    POSITIVE LOGITS
    itsch
    0.96
     et
    0.75
     Aad
    0.72
    retty
    0.71
     pers
    0.70
    earchers
    0.69
    âĵĺ
    0.68
    ritional
    0.66
    oneliness
    0.65
     Handbook
    0.65
    Activations Density 0.131%

    No Known Activations