© 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. 2-RES-JB
    11. 4224
    Prev
    Next
    INDEX
    Explanations

    mentions of rankings or positions based on performance or status

    oai_token-act-pair · gpt-3.5-turbo

    references to prizes and awards, often linked with a context of emphasis or importance

    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
     Nas
    -0.82
     Queen
    -0.76
    amiya
    -0.73
    é¾įåĸļ士
    -0.69
    RED
    -0.68
     Pend
    -0.66
    ERA
    -0.66
    abul
    -0.66
     Nest
    -0.65
    ãĤ¢ãĥ«
    -0.65
    POSITIVE LOGITS
     pri
    1.13
     corrid
    0.89
    ŃĶ
    0.81
    teenth
    0.79
     confir
    0.78
     prem
    0.78
     experien
    0.75
    ģ«
    0.75
    İĭ
    0.75
    Ħ¢
    0.74
    Activations Density 0.016%

    No Known Activations