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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 6395
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "came across"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "came across."

    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
    wake
    -0.68
    pressure
    -0.67
    ģĸ
    -0.66
    leave
    -0.65
    Wire
    -0.65
    cise
    -0.64
    ikarp
    -0.64
    arily
    -0.63
    jri
    -0.63
    za
    -0.63
    POSITIVE LOGITS
     inconsistencies
    0.77
     objectionable
    0.75
     something
    0.75
     contradictions
    0.74
     clues
    0.73
     kindred
    0.72
     glimps
    0.71
     resemb
    0.67
     Craigslist
    0.66
     irregularities
    0.66
    Activations Density 0.103%

    No Known Activations