Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1654
    Prev
    Next
    INDEX
    Explanations

    adverbs modifying ease or difficulty

    oai_token-act-pair · gpt-3.5-turbo

    the adverb "easily"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.84
    grave
    -0.81
     Millennium
    -0.71
    iosity
    -0.70
    quality
    -0.69
    anwhile
    -0.69
    spin
    -0.68
    raints
    -0.68
    rum
    -0.67
    Moon
    -0.67
    POSITIVE LOGITS
    Jet
    0.86
     easily
    0.86
     identifiable
    0.85
     prey
    0.79
     accommod
    0.77
     enough
    0.76
     accessible
    0.76
     readable
    0.75
     distingu
    0.75
     achievable
    0.74
    Activations Density 0.010%

    No Known Activations