© 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. 14921
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic relations between two countries

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to the concept of relationships between two entities

    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
    atown
    -0.71
    racuse
    -0.70
     Caption
    -0.69
    aukee
    -0.68
    ugu
    -0.68
    asta
    -0.66
    gallery
    -0.66
    aii
    -0.65
    ick
    -0.65
    ahoo
    -0.64
    POSITIVE LOGITS
     halves
    1.12
     sexes
    1.03
     thirds
    0.97
    fold
    0.84
     sides
    0.77
     brothers
    0.77
     Kore
    0.76
     aforementioned
    0.74
     dozen
    0.73
     genders
    0.72
    Activations Density 0.076%

    No Known Activations