© 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. 8-RES-JB
    11. 18733
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast and comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a comparison or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uble
    -0.74
    enos
    -0.72
    amon
    -0.67
    atile
    -0.66
    erest
    -0.65
     Clicker
    -0.63
    olis
    -0.62
    esome
    -0.62
    acha
    -0.61
    nce
    -0.60
    POSITIVE LOGITS
     preferably
    0.83
    etheless
    0.77
     excluding
    0.75
    cause
    0.75
     coerc
    0.72
     evidenced
    0.72
     preferring
    0.71
    ardless
    0.69
     including
    0.68
     theirs
    0.68
    Activations Density 0.290%

    No Known Activations