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. 6588
    Prev
    Next
    INDEX
    Explanations

    phrases related to direct eye contact

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    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
    olicy
    -0.75
    ional
    -0.69
    itus
    -0.67
    arians
    -0.67
    anova
    -0.67
    nance
    -0.65
    abe
    -0.64
    acca
    -0.63
    nesty
    -0.62
    ulner
    -0.62
    POSITIVE LOGITS
     midst
    1.43
     meantime
    1.33
     vicinity
    1.25
     slightest
    1.20
     aftermath
    1.09
     middle
    1.07
     guise
    1.05
     same
    1.05
     afterlife
    1.01
     simplest
    0.98
    Activations Density 0.300%

    No Known Activations