© 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. 9-RES-JB
    11. 16132
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moreover
    -0.75
    icides
    -0.74
    ubi
    -0.73
    bath
    -0.70
    only
    -0.68
    iday
    -0.67
    Likewise
    -0.67
    Furthermore
    -0.66
    module
    -0.65
     additionally
    -0.65
    POSITIVE LOGITS
     pret
    0.71
     decency
    0.65
    former
    0.64
     pretend
    0.60
     foreseeable
    0.60
     acknowledgement
    0.59
     insofar
    0.59
     basics
    0.59
     sane
    0.57
     temporarily
    0.56
    Activations Density 0.097%

    No Known Activations