© 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. 6-RES-JB
    11. 13514
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone has secured a position or status in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a position or location within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gery
    -0.75
    aeus
    -0.72
    duct
    -0.67
    catch
    -0.67
    use
    -0.66
    selves
    -0.64
    clone
    -0.63
    owner
    -0.62
     neglig
    -0.62
    ully
    -0.62
    POSITIVE LOGITS
     pedest
    0.78
     theaters
    0.75
     prestigious
    0.74
    elight
    0.72
     UNESCO
    0.71
     RTX
    0.68
     civilized
    0.68
     exalted
    0.67
     Nanto
    0.66
     Normandy
    0.66
    Activations Density 0.323%

    No Known Activations