© 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. 8-RES-JB
    11. 745
    Prev
    Next
    INDEX
    Explanations

    instances of the word "platform"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of platforms

    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
    nexus
    -0.77
     quarters
    -0.69
     Reduction
    -0.68
     iod
    -0.64
    ãĤĬ
    -0.63
     circumcised
    -0.63
     Wass
    -0.63
    SEE
    -0.63
    ãĤĵ
    -0.62
     Rays
    -0.61
    POSITIVE LOGITS
     platforms
    0.94
     platform
    0.84
    folios
    0.79
    ioned
    0.79
    onite
    0.78
    hip
    0.75
    folio
    0.75
    etter
    0.72
    atility
    0.70
    er
    0.67
    Activations Density 0.036%

    No Known Activations