© 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. 7-RES-JB
    11. 8668
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oufl
    -0.77
     typh
    -0.74
    agin
    -0.74
    anus
    -0.74
    asus
    -0.72
    vas
    -0.72
    gins
    -0.69
     tremend
    -0.66
     glands
    -0.65
     Accessed
    -0.65
    POSITIVE LOGITS
     unanimously
    0.82
    ably
    0.80
    rences
    0.75
     disagree
    0.74
     Rate
    0.71
    lihood
    0.70
    agree
    0.69
     vehemently
    0.67
     agrees
    0.65
    SOURCE
    0.65
    Activations Density 0.031%

    No Known Activations