© 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. 1-RES-JB
    11. 1038
    Prev
    Next
    INDEX
    Explanations

    references to specific football conference abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    references to the NFC (National Football Conference) in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.84
    lift
    -0.80
    conserv
    -0.73
    Reviewer
    -0.72
    andr
    -0.72
    76561
    -0.69
    lly
    -0.69
    emort
    -0.69
    itars
    -0.68
    iard
    -0.67
    POSITIVE LOGITS
     NFC
    1.44
    Ĥª
    0.83
    oji
    0.76
    TERN
    0.74
     AFC
    0.73
    ECA
    0.70
    ribes
    0.69
     junction
    0.69
    rypted
    0.68
     NX
    0.67
    Activations Density 0.007%

    No Known Activations