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. 10-RES-JB
    6. 9227
    Prev
    Next
    INDEX
    Explanations

    mentions of someone's first instance/experience with a particular event or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "first" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bara
    -0.82
    holes
    -0.79
    tics
    -0.75
    stairs
    -0.71
     Mahm
    -0.68
    ppings
    -0.66
     Vish
    -0.66
    still
    -0.65
    owers
    -0.65
    skirts
    -0.62
    POSITIVE LOGITS
     foray
    1.48
     outing
    1.15
     stint
    1.06
     appearance
    1.02
     attempt
    0.95
     encounter
    0.93
     incarnation
    0.91
     trip
    0.88
     visit
    0.88
     glimpse
    0.86
    Activations Density 0.094%

    No Known Activations