© 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. 8-RES-JB
    11. 619
    Prev
    Next
    INDEX
    Explanations

    visual or multimedia content that requires JavaScript to be enabled

    oai_token-act-pair · gpt-3.5-turbo

    content related to watching videos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.79
    ament
    -0.69
    sonian
    -0.69
    iety
    -0.64
    christ
    -0.62
    ruary
    -0.60
    hend
    -0.60
    orah
    -0.60
    plan
    -0.60
    stellar
    -0.59
    POSITIVE LOGITS
     restricted
    0.67
     Firearms
    0.63
    Afee
    0.63
     unlimited
    0.61
     isEnabled
    0.59
     disabling
    0.59
     offline
    0.58
    encer
    0.58
    ļéĨĴ
    0.57
    Video
    0.57
    Activations Density 0.041%

    No Known Activations