© 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. 4-RES-JB
    11. 17005
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences and actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of experiences and accomplishments

    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
     Axis
    -0.67
     Commodore
    -0.63
    States
    -0.62
    vals
    -0.62
    Britain
    -0.61
     Wiley
    -0.61
    Analysis
    -0.60
     Winston
    -0.59
     Allied
    -0.59
    root
    -0.58
    POSITIVE LOGITS
    ãĤ¦ãĤ¹
    0.73
    cedented
    0.72
    atars
    0.71
     doi
    0.68
     deleted
    0.68
    =""
    0.67
     (@
    0.65
    ttes
    0.63
    ãĤ¼ãĤ¦ãĤ¹
    0.63
     tears
    0.63
    Activations Density 0.085%

    No Known Activations