© 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. 2-RES-JB
    11. 8289
    Prev
    Next
    INDEX
    Explanations

    phrases related to spouses or partners

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obyl
    -0.77
    McC
    -0.73
    yss
    -0.73
    ostic
    -0.70
     handc
    -0.69
     Barkley
    -0.66
    ortmund
    -0.64
     Flavoring
    -0.64
    XP
    -0.64
     contam
    -0.63
    POSITIVE LOGITS
    husband
    1.01
    friend
    0.98
    hood
    0.88
    pins
    0.86
     husband
    0.81
    wife
    0.81
    pin
    0.76
    hesis
    0.75
    mingham
    0.74
    loo
    0.73
    Activations Density 0.013%

    No Known Activations