© 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. 2-RES-JB
    11. 12834
    Prev
    Next
    INDEX
    Explanations

    keywords related to industries such as aerospace, automotive, and cybersecurity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aerospace, cybersecurity, and STEM fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.84
    naire
    -0.81
    steen
    -0.81
    ifest
    -0.78
    enment
    -0.77
    heim
    -0.72
    gered
    -0.71
     Metatron
    -0.71
    atra
    -0.71
    ovich
    -0.70
    POSITIVE LOGITS
     professionals
    0.92
     sciences
    0.91
     feasibility
    0.88
     pursuits
    0.87
     literature
    0.86
     literacy
    0.86
    querque
    0.82
     engineering
    0.82
     practition
    0.81
     specialists
    0.81
    Activations Density 0.031%

    No Known Activations