© 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. 9-RES-JB
    11. 21196
    Prev
    Next
    INDEX
    Explanations

    references to a specific country

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "this" in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icons
    -0.80
    marks
    -0.77
    acers
    -0.76
     Pwr
    -0.74
    emis
    -0.72
    apses
    -0.71
    ickets
    -0.70
    asures
    -0.67
    Examples
    -0.67
    aws
    -0.66
    POSITIVE LOGITS
     regard
    1.11
     country
    1.04
     hemisphere
    1.03
     century
    1.01
     particular
    0.96
     trope
    0.92
     continent
    0.90
     decade
    0.88
     millennium
    0.87
    uncture
    0.86
    Activations Density 0.154%

    No Known Activations