Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23590
    Prev
    Next
    INDEX
    Explanations

    terms related to directional movements or locations

    oai_token-act-pair · gpt-3.5-turbo

    directional terms related to location and movement

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

    No Comments

    Negative Logits
    ocular
    -0.90
    obook
    -0.77
    gdala
    -0.75
    natureconservancy
    -0.73
    colo
    -0.72
    oxide
    -0.69
     Guinness
    -0.67
    coni
    -0.66
    alogue
    -0.65
    ĸļ
    -0.64
    POSITIVE LOGITS
    robe
    0.98
    ward
    0.92
    ness
    0.92
    ly
    0.87
    ments
    0.81
    wards
    0.80
    nesses
    0.78
    enger
    0.72
    eous
    0.72
     Spiral
    0.71
    Activations Density 0.009%

    No Known Activations