© 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. 3-RES-JB
    11. 11303
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Samar" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the region of Samar

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAFT
    -1.08
    ered
    -0.77
    brainer
    -0.74
    yers
    -0.71
    enegger
    -0.70
    anwhile
    -0.70
    ORN
    -0.70
    puff
    -0.69
    sheet
    -0.69
    piracy
    -0.69
    POSITIVE LOGITS
    itans
    1.11
     Samar
    1.09
    itan
    1.07
     Kou
    0.82
    pling
    0.78
    autions
    0.75
    eness
    0.74
    pha
    0.72
    agi
    0.71
    ©¶æ
    0.71
    Activations Density 0.004%

    No Known Activations