© 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. 10-RES-JB
    11. 13591
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and discrediting

    oai_token-act-pair · gpt-3.5-turbo

    ellipsis or unfinished thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fide
    -0.67
     outl
    -0.67
     merit
    -0.67
     oxide
    -0.62
     attest
    -0.62
     peripher
    -0.62
     cultiv
    -0.61
    opath
    -0.61
     claimants
    -0.59
     finance
    -0.59
    POSITIVE LOGITS
    until
    1.26
    but
    1.18
    they
    1.15
    again
    1.15
    yeah
    1.13
    BUT
    1.13
    yet
    1.13
    except
    1.12
    then
    1.12
    etc
    1.12
    Activations Density 0.040%

    No Known Activations