© 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. 4-RES-JB
    11. 15215
    Prev
    Next
    INDEX
    Explanations

    words related to different variations of the name "Alves"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or entities involved in an inquiry

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

    No Comments

    Negative Logits
    board
    -0.69
    boards
    -0.68
     awarding
    -0.67
    wcs
    -0.67
     hop
    -0.66
     cannabin
    -0.65
     carbohyd
    -0.63
    olicy
    -0.63
     affiliation
    -0.63
     BAS
    -0.63
    POSITIVE LOGITS
    ieve
    1.12
    ulf
    0.87
    bians
    0.86
    olve
    0.84
    olutions
    0.82
    ault
    0.82
    erve
    0.81
    ync
    0.80
    olution
    0.80
    ongs
    0.79
    Activations Density 0.011%

    No Known Activations