© 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. 1-RES-JB
    11. 3822
    Prev
    Next
    INDEX
    Explanations

    references to admission or allowing entry

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "admission."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srf
    -0.68
    rodu
    -0.64
     repetitive
    -0.64
     autonomous
    -0.63
     chromosomes
    -0.62
     sensed
    -0.61
     unpredictable
    -0.60
     indust
    -0.60
    lette
    -0.60
    hed
    -0.60
    POSITIVE LOGITS
     admission
    1.32
     Admission
    1.21
     admissions
    1.06
    ysis
    0.97
    aneers
    0.79
    prise
    0.79
    Reviewer
    0.78
    opoulos
    0.77
    glers
    0.76
    ibility
    0.74
    Activations Density 0.005%

    No Known Activations