© 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. 7-RES-JB
    11. 20765
    Prev
    Next
    INDEX
    Explanations

    specific spatial locations and relationships within objects

    oai_token-act-pair · gpt-3.5-turbo

    components and attributes related to products or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arcity
    -1.11
    Ô
    -0.84
    aneers
    -0.80
    Boo
    -0.78
    Independent
    -0.75
    ontent
    -0.74
    HCR
    -0.73
    urdue
    -0.73
    Merit
    -0.73
    quest
    -0.72
    POSITIVE LOGITS
     cheeks
    1.07
     abdomen
    1.06
     forehead
    1.04
     casing
    0.99
     underside
    0.98
     periphery
    0.97
     wrists
    0.97
     hips
    0.94
     corners
    0.94
     torso
    0.93
    Activations Density 0.323%

    No Known Activations