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. 2-RES-JB
    6. 2299
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical attributes or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to physical conditions or physical experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffic
    -0.68
    ered
    -0.68
     Tul
    -0.68
    ilts
    -0.67
    andel
    -0.66
    lr
    -0.65
    stakes
    -0.65
     Aval
    -0.65
     Gos
    -0.65
     Chance
    -0.64
    POSITIVE LOGITS
    anguage
    0.82
     assaulted
    0.80
     cumbers
    0.80
     assaulting
    0.76
     illiter
    0.74
     speaking
    0.73
     handic
    0.72
     altercation
    0.69
    TPPStreamerBot
    0.69
     conclud
    0.68
    Activations Density 0.005%

    No Known Activations