Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24140
    Prev
    Next
    INDEX
    Explanations

    terms related to political discussions around immigration

    oai_token-act-pair · gpt-3.5-turbo

    mentions of immigration policy and reform discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilts
    -0.83
    MpServer
    -0.82
    eenth
    -0.80
    oeuv
    -0.77
    sonian
    -0.76
    å§«
    -0.75
    âĶĢâĶĢ
    -0.75
    olls
    -0.74
    Ò
    -0.73
    IVES
    -0.73
    POSITIVE LOGITS
     immigration
    1.05
     detention
    1.04
     visas
    0.96
     deportation
    0.89
     reform
    0.87
     Detention
    0.86
     amnesty
    0.86
     deported
    0.86
     immigrants
    0.86
     Immigration
    0.84
    Activations Density 0.025%

    No Known Activations