© 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. 11-RES-JB
    11. 18740
    Prev
    Next
    INDEX
    Explanations

    references to technological platforms or the act of platforming in a digital context

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "platform" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vol
    -0.67
    SEE
    -0.66
    nexus
    -0.64
    nery
    -0.64
    itate
    -0.63
    itated
    -0.63
    VID
    -0.61
    pee
    -0.61
    aukee
    -0.59
     Flames
    -0.59
    POSITIVE LOGITS
     platform
    0.89
     platforms
    0.88
    er
    0.84
    etter
    0.81
    hare
    0.77
    atform
    0.75
     holder
    0.75
    atility
    0.74
    ing
    0.73
     Platform
    0.73
    Activations Density 0.033%

    No Known Activations