© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16184
    Prev
    Next
    INDEX
    Explanations

    mentions of Motorola smartphones

    oai_token-act-pair · gpt-3.5-turbo
    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
    igree
    -0.85
    itable
    -0.83
    ipeg
    -0.81
    ition
    -0.81
    tnc
    -0.79
    irk
    -0.78
    imental
    -0.76
    elaide
    -0.76
    ience
    -0.75
    iments
    -0.74
    POSITIVE LOGITS
    GP
    1.04
    cycle
    0.92
     Moto
    0.91
    cycles
    0.89
    XM
    0.85
     Maker
    0.83
     Mods
    0.82
     Mobility
    0.78
    åİ
    0.75
    zzi
    0.75
    Activations Density 0.038%

    No Known Activations