© 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. 10180
    Prev
    Next
    INDEX
    Explanations

    words related to immigration and emigration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to immigration and migration processes

    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
    arius
    -0.74
    pering
    -0.72
    peer
    -0.71
    eq
    -0.69
    chair
    -0.68
    pit
    -0.67
    reme
    -0.66
    equal
    -0.66
    osure
    -0.65
    iac
    -0.64
    POSITIVE LOGITS
     visas
    1.04
     abroad
    0.98
     visa
    0.93
     immigrants
    0.89
     UNHCR
    0.89
     immigrant
    0.83
     deported
    0.80
    igrated
    0.79
     Filipino
    0.78
     passports
    0.76
    Activations Density 0.067%

    No Known Activations