© 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. 4130
    Prev
    Next
    INDEX
    Explanations

    references to a specific location, which is Derby

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports events or competitions, particularly focusing on "Derby" related activities

    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
     Ng
    -0.77
    perse
    -0.75
    ordan
    -0.74
     Kub
    -0.70
     Wales
    -0.70
    bang
    -0.69
     Kamp
    -0.67
    llan
    -0.66
    iang
    -0.65
    resh
    -0.65
    POSITIVE LOGITS
     Derby
    2.40
     Keystone
    2.23
     derby
    1.84
     Bieber
    1.40
     Grande
    1.34
     Genie
    1.24
     Drake
    1.22
     Steele
    1.19
     Bie
    1.17
     selfie
    1.09
    Activations Density 0.038%

    No Known Activations