© 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. 15297
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Japanese politics, particularly focusing on the surname 'Abe'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those named Abe

    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
    onyms
    -0.82
    porting
    -0.74
    ippi
    -0.72
    oner
    -0.71
     Appalach
    -0.67
     McKenna
    -0.66
     RTX
    -0.65
    othal
    -0.64
    ivity
    -0.63
    ODUCT
    -0.63
    POSITIVE LOGITS
     Shinzo
    1.17
     Abe
    1.02
    cean
    1.02
    eln
    0.88
     plur
    0.86
    ijing
    0.77
    achev
    0.77
    wake
    0.75
    elia
    0.73
     nodd
    0.73
    Activations Density 0.006%

    No Known Activations