© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 16634
    Prev
    Next
    INDEX
    Explanations

    items of clothing or accessories

    oai_token-act-pair · gpt-3.5-turbo

    specific physical objects or locations described in a spatial context

    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
    Specific
    -0.50
    Month
    -0.49
    çīĪ
    -0.48
     referen
    -0.48
    ĻĤ
    -0.47
    Function
    -0.46
    uable
    -0.46
    Fact
    -0.46
     Referred
    -0.45
     qualitative
    -0.44
    POSITIVE LOGITS
     overlooking
    0.59
     shack
    0.57
     ropes
    0.56
     bowl
    0.53
     beside
    0.53
     railing
    0.53
    stretched
    0.52
    hes
    0.50
    cloth
    0.49
     hut
    0.49
    Activations Density 0.938%

    No Known Activations