© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 7599
    Prev
    Next
    INDEX
    Explanations

    technical specifications and mechanical details

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to engineering components or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sudan
    -0.89
     Cruel
    -0.80
     Salvation
    -0.77
     Yemen
    -0.75
     Covenant
    -0.74
     innocence
    -0.74
     Somalia
    -0.73
     Somali
    -0.72
     dreams
    -0.71
     anarch
    -0.70
    POSITIVE LOGITS
    imeter
    1.19
    imeters
    1.10
    mounted
    1.07
    Motor
    1.03
    itech
    0.99
    lite
    0.99
     adjustable
    0.98
    meter
    0.97
    amping
    0.97
    onet
    0.96
    Activations Density 0.346%

    No Known Activations