© 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. 8-RES-JB
    11. 19322
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a specific location or context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or contexts in which events or actions occur

    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
    onna
    -0.72
    ulence
    -0.67
     Uriel
    -0.64
    rex
    -0.63
    gery
    -0.63
    agascar
    -0.59
    ammy
    -0.59
    arcity
    -0.58
    apest
    -0.58
     Taxes
    -0.58
    POSITIVE LOGITS
     confines
    1.72
     bounds
    1.46
     boundaries
    1.24
     limits
    1.09
     borders
    1.02
     scope
    0.99
     walls
    0.97
     parameters
    0.95
     radius
    0.95
     realm
    0.92
    Activations Density 0.163%

    No Known Activations