© 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. 10-RES-JB
    11. 9892
    Prev
    Next
    INDEX
    Explanations

    government agencies, organizations, and commissions

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or regulatory bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¦
    -0.63
    kell
    -0.63
    appings
    -0.62
    "]=>
    -0.62
    lan
    -0.62
    mode
    -0.61
     experien
    -0.61
    rises
    -0.60
    estamp
    -0.59
    lang
    -0.58
    POSITIVE LOGITS
     (
    0.85
    's
    0.84
     ("
    0.80
     Directorate
    0.77
     Appropriations
    0.74
     (.
    0.74
     headquartered
    0.72
     Employees
    0.71
     ($
    0.70
     Task
    0.70
    Activations Density 0.188%

    No Known Activations