© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 13210
    Prev
    Next
    INDEX
    Explanations

    phrases indicating equivalences or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of equivalence or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clus
    -0.71
    tnc
    -0.71
    rust
    -0.70
    oner
    -0.70
    arth
    -0.70
    vae
    -0.65
    evin
    -0.61
     candid
    -0.61
     Joined
    -0.60
    heimer
    -0.60
    POSITIVE LOGITS
     equivalent
    4.17
     equivalents
    2.94
     equival
    1.98
     comparable
    1.82
     analogous
    1.76
     counterpart
    1.51
    ivalent
    1.45
     equal
    1.31
     counterparts
    1.28
     analogue
    1.23
    Activations Density 0.016%

    No Known Activations