© 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. 23903
    Prev
    Next
    INDEX
    Explanations

    phrases related to general statements or actions applying universally

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity or collective experience

    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
    tnc
    -0.68
    word
    -0.66
     testament
    -0.62
     hints
    -0.61
     Testament
    -0.58
    zek
    -0.57
    enture
    -0.57
    ories
    -0.56
    veyard
    -0.56
     Nanto
    -0.56
    POSITIVE LOGITS
     else
    1.78
    else
    1.31
     Else
    1.26
     involved
    1.18
     except
    1.06
    Else
    1.05
    involved
    0.90
     imaginable
    0.86
     who
    0.85
    soever
    0.84
    Activations Density 0.083%

    No Known Activations