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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 23878
    Prev
    Next
    INDEX
    Explanations

    phrases comparing similarities or equivalences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to comparisons and similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isec
    -0.72
    eni
    -0.64
    sort
    -0.63
    akeru
    -0.63
    Soft
    -0.63
    iband
    -0.62
    Finish
    -0.62
    nice
    -0.60
    ritis
    -0.60
    hene
    -0.57
    POSITIVE LOGITS
     ours
    1.53
     those
    1.45
     theirs
    1.34
     hers
    1.26
     yours
    1.22
     that
    1.15
    those
    1.12
     mine
    1.09
    that
    0.95
     THAT
    0.84
    Activations Density 0.191%

    No Known Activations