© 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. 9152
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, particularly focusing on Cambodia and individuals' names related to the area

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Cambodia and its associated contexts

    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
    ifying
    -0.83
    mond
    -0.81
    ific
    -0.80
    bow
    -0.78
    aciously
    -0.76
    zzle
    -0.76
    aging
    -0.74
     Hurricanes
    -0.73
    igo
    -0.71
    ifiable
    -0.71
    POSITIVE LOGITS
    ĺħ
    0.83
    Ħ¢
    0.77
    ulhu
    0.76
     MacDonald
    0.76
    Ģ
    0.74
    emouth
    0.73
    ritic
    0.71
    yip
    0.71
    rift
    0.71
     Cambod
    0.70
    Activations Density 0.032%

    No Known Activations