© 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. 2-RES-JB
    11. 13022
    Prev
    Next
    INDEX
    Explanations

    exact matches of the word "exactly" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize certainty or specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -0.83
    rift
    -0.72
    Reviewer
    -0.70
     Marcos
    -0.65
    kers
    -0.64
     Guys
    -0.63
    liest
    -0.63
    jay
    -0.61
    ULTS
    -0.60
    edu
    -0.60
    POSITIVE LOGITS
    actly
    0.73
     ident
    0.72
     opposite
    0.70
     exactly
    0.70
     chronological
    0.68
    itude
    0.68
    yrinth
    0.67
    uracy
    0.67
    cellence
    0.65
     Exactly
    0.65
    Activations Density 0.011%

    No Known Activations