© 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. 3698
    Prev
    Next
    INDEX
    Explanations

    comparisons and assessments using the word "as" to link two ideas

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express varying degrees of absurdity or incredibility

    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
    between
    -0.72
    FTWARE
    -0.69
     srfAttach
    -0.68
    famous
    -0.67
    lasting
    -0.64
    fund
    -0.63
    isoft
    -0.63
    last
    -0.62
    ICO
    -0.61
    iller
    -0.60
    POSITIVE LOGITS
     sounds
    0.71
    lihood
    0.69
     intentions
    0.67
     may
    0.65
    sounding
    0.62
     sounding
    0.61
     prose
    0.61
     might
    0.60
     doubtless
    0.60
    iHUD
    0.60
    Activations Density 0.125%

    No Known Activations