© 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. 11-RES-JB
    11. 1089
    Prev
    Next
    INDEX
    Explanations

    surnames of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.72
    series
    -0.65
    leep
    -0.64
    window
    -0.62
    classic
    -0.60
    ãĥīãĥ©
    -0.59
    burning
    -0.58
    ãĤ¤ãĥĪ
    -0.58
    stream
    -0.58
    ãĤĵ
    -0.57
    POSITIVE LOGITS
     believes
    1.16
     likened
    1.16
     added
    1.14
     emphasized
    1.14
     stressed
    1.13
     cautioned
    1.12
     elaborated
    1.11
     pointed
    1.09
     also
    1.08
     contrasted
    1.08
    Activations Density 0.190%

    No Known Activations