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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 20662
    Prev
    Next
    INDEX
    Explanations

    keywords related to the concept of gravity, such as "gravity" and "gravitational pull."

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to gravity and gravitational forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ointed
    -0.84
    imony
    -0.80
    tery
    -0.79
    anie
    -0.77
    rahim
    -0.77
    ership
    -0.72
    ts
    -0.72
    ublic
    -0.71
    olog
    -0.70
    antha
    -0.69
    POSITIVE LOGITS
     gravity
    1.03
     cooker
    0.87
     acceleration
    0.82
     helium
    0.82
    gravity
    0.81
     resonance
    0.81
     distortion
    0.81
     sickness
    0.81
     anomaly
    0.81
     curv
    0.80
    Activations Density 0.040%

    No Known Activations