© 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. 1-RES-JB
    11. 14334
    Prev
    Next
    INDEX
    Explanations

    the name "Johnny"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly Johnny Manziel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oral
    -0.93
    sky
    -0.80
    hips
    -0.76
    liga
    -0.76
    hops
    -0.75
    lied
    -0.73
    ional
    -0.73
    orius
    -0.73
    recomm
    -0.73
    ered
    -0.73
    POSITIVE LOGITS
     Manziel
    1.05
     Johnny
    0.98
     Yong
    0.85
     Rico
    0.82
     Sins
    0.77
    ppo
    0.75
    Johnny
    0.74
     Moran
    0.74
    bum
    0.73
    prus
    0.72
    Activations Density 0.011%

    No Known Activations