© 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. 6-RES-JB
    11. 19738
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or groups experiencing displacements due to various circumstances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to displacement and refugees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ature
    -0.81
    vern
    -0.75
    atur
    -0.72
    acca
    -0.71
    bara
    -0.70
    getic
    -0.68
    ramid
    -0.65
    osterone
    -0.65
    ysis
    -0.64
    tarian
    -0.63
    POSITIVE LOGITS
     refugees
    0.96
     displaced
    0.88
     migrants
    0.81
     refugee
    0.79
     fleeing
    0.77
     Refugees
    0.77
     orphans
    0.74
    pora
    0.71
     displacement
    0.71
     Refugee
    0.70
    Activations Density 0.031%

    No Known Activations