© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 9466
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific company names starting with the letter "G"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'G' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.72
    ansas
    -0.65
    orah
    -0.60
    awareness
    -0.59
    cases
    -0.59
     anyways
    -0.59
    ographed
    -0.58
    thur
    -0.57
    cation
    -0.57
    cube
    -0.57
    POSITIVE LOGITS
     G
    3.02
    G
    2.08
     g
    1.62
     GS
    1.42
     GF
    1.33
    g
    1.32
    Gs
    1.25
     GT
    1.21
     GH
    1.19
    GS
    1.18
    Activations Density 0.033%

    No Known Activations