© 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. 2-RES-JB
    11. 7196
    Prev
    Next
    INDEX
    Explanations

    identifiers related to specific technologies or people, possibly in a tech context

    oai_token-act-pair · gpt-3.5-turbo

    references to video game technology and specific individuals related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mosqu
    -0.74
    upe
    -0.67
    andum
    -0.65
     Brav
    -0.63
     Pon
    -0.63
     exha
    -0.63
     verbs
    -0.62
    cius
    -0.62
     conduc
    -0.62
    abilia
    -0.62
    POSITIVE LOGITS
     DX
    0.89
     DirectX
    0.86
    DX
    0.78
    ounded
    0.71
    forth
    0.70
     dx
    0.69
    ressed
    0.69
     2048
    0.68
    è£ħ
    0.67
    RGB
    0.67
    Activations Density 0.025%

    No Known Activations