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

    Neuronpedia

    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. 0-RES-JB
    11. 10110
    Prev
    Next
    INDEX
    Explanations

    locations or places, particularly cities or towns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with locations and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     profiling
    -0.69
     differentiation
    -0.68
     tube
    -0.67
    LINE
    -0.66
    system
    -0.66
     tunnel
    -0.65
     ATM
    -0.65
    FIELD
    -0.64
     infiltr
    -0.64
     filters
    -0.63
    POSITIVE LOGITS
     Grac
    1.79
     Preview
    1.36
     Worth
    1.34
     Hick
    1.32
    opot
    1.27
     Rouse
    1.24
     Sturgeon
    1.22
     Guinea
    1.20
     Rousse
    1.15
     Naw
    1.10
    Activations Density 0.052%

    No Known Activations