© 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. 4-RES-JB
    11. 6199
    Prev
    Next
    INDEX
    Explanations

    references to AFL (Australian Football League) teams or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the AFL (Australian Football League)

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

    No Comments

    Negative Logits
    anamo
    -0.84
    imens
    -0.83
     Tsarnaev
    -0.81
    imaru
    -0.75
    adow
    -0.74
    fulness
    -0.72
     Mercer
    -0.72
    imura
    -0.70
    ned
    -0.70
    ãĤ®
    -0.69
    POSITIVE LOGITS
    RL
    0.85
    ORD
    0.80
    WA
    0.78
     AFL
    0.77
    elaide
    0.76
    UTH
    0.76
     unions
    0.75
    YL
    0.70
    APTER
    0.70
    UST
    0.69
    Activations Density 0.006%

    No Known Activations