© 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. 1-RES-JB
    11. 9486
    Prev
    Next
    INDEX
    Explanations

    terms related to the Information Technology (IT) industry

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the IT industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ©ãĥ³
    -0.77
    toggle
    -0.73
    charged
    -0.70
     Sioux
    -0.70
     Barker
    -0.68
     Kuwait
    -0.67
     Dayton
    -0.67
    warning
    -0.67
     Sul
    -0.65
     Towns
    -0.65
    POSITIVE LOGITS
    IME
    0.97
    EMS
    0.97
    iago
    0.91
    anium
    0.88
    unes
    0.86
     outsourcing
    0.82
    EM
    0.82
     resil
    0.82
    HAEL
    0.81
     mathemat
    0.79
    Activations Density 0.006%

    No Known Activations