© 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. 20396
    Prev
    Next
    INDEX
    Explanations

    services, companies, and entities related to technology and business

    oai_token-act-pair · gpt-3.5-turbo

    terms related to online services and platforms

    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
    éŃĶ
    -0.76
    izoph
    -0.76
    cffffcc
    -0.75
    bat
    -0.74
    ãģĦ
    -0.72
    romy
    -0.68
    damage
    -0.64
    izophren
    -0.63
    ãĥĥãĥī
    -0.62
    material
    -0.62
    POSITIVE LOGITS
     specializing
    1.05
     headquartered
    0.98
     catering
    0.89
     operator
    0.89
     frequ
    0.85
     operators
    0.85
     founded
    0.83
     Tycoon
    0.83
     provider
    0.81
     staffed
    0.78
    Activations Density 0.261%

    No Known Activations