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. 4-RES-JB
    6. 5128
    Prev
    Next
    INDEX
    Explanations

    words related to electronic communication and actions involving sending or receiving information

    oai_token-act-pair · gpt-3.5-turbo

    words related to forms and suffixes in English

    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
    pport
    -0.67
     nerv
    -0.66
    hus
    -0.63
    zan
    -0.61
    QUI
    -0.61
    bite
    -0.60
    gas
    -0.60
    odox
    -0.59
    andra
    -0.59
    bush
    -0.58
    POSITIVE LOGITS
     INTO
    0.90
     Away
    0.76
     Into
    0.74
     Ahead
    0.68
    forward
    0.66
     onward
    0.66
     authenticated
    0.63
     undone
    0.63
     Signed
    0.63
    engers
    0.62
    Activations Density 0.098%

    No Known Activations