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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2930
    Prev
    Next
    INDEX
    Explanations

    references to glass items or features

    oai_token-act-pair · gpt-3.5-turbo

    references to glass in various contexts

    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
     Leilan
    -0.81
    addr
    -0.75
    nr
    -0.71
     RELE
    -0.70
     Resp
    -0.69
    reon
    -0.68
    rosso
    -0.68
     Sequ
    -0.68
    respond
    -0.67
     Nationals
    -0.67
    POSITIVE LOGITS
     glass
    3.73
    Glass
    2.55
    glass
    2.55
     Glass
    2.44
     glasses
    2.19
     champagne
    1.35
     ceramic
    1.34
     plastic
    1.30
     windshield
    1.29
     bottle
    1.28
    Activations Density 0.021%

    No Known Activations