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

    Neuronpedia

    Jacobian LensNEW
    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. 20312
    Prev
    Next
    INDEX
    Explanations

    names or terms related to individuals named "Mir"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific name or identifier, likely related to an individual or topic of interest

    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
    ential
    -0.75
     Combine
    -0.66
     Primordial
    -0.63
     LCS
    -0.62
     Merrill
    -0.60
     Heritage
    -0.59
     Adamant
    -0.59
     Panther
    -0.58
    CAST
    -0.57
     Dynam
    -0.56
    POSITIVE LOGITS
    rored
    1.38
    rors
    1.34
    acles
    1.34
    acle
    1.25
    abilia
    1.09
    abella
    1.07
    ror
    1.02
    abel
    0.94
    iam
    0.94
    abil
    0.91
    Activations Density 0.033%

    No Known Activations