© 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. 11-RES-JB
    11. 2526
    Prev
    Next
    INDEX
    Explanations

    phrases related to asylum seekers and immigration issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to asylum seekers and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Press
    -0.74
    ointed
    -0.73
     Cool
    -0.69
     Publishing
    -0.67
     Parameters
    -0.66
    urated
    -0.66
    Awesome
    -0.65
     Fires
    -0.64
    Alright
    -0.63
     Precision
    -0.63
    POSITIVE LOGITS
     deserve
    1.32
     suffer
    1.19
     langu
    1.17
     pose
    1.16
     fled
    1.15
     flee
    1.15
     belong
    1.12
     reside
    1.12
     fleeing
    1.10
     qualify
    1.08
    Activations Density 0.375%

    No Known Activations