© 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. 3-RES-JB
    11. 1964
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative events or situations

    oai_token-act-pair · gpt-3.5-turbo

    words and concepts related to direction and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Height
    -0.48
     Thing
    -0.46
     Month
    -0.44
     Qual
    -0.44
     Me
    -0.43
     Contribut
    -0.43
     Moving
    -0.42
     Acqu
    -0.42
     Corridor
    -0.42
     Rank
    -0.42
    POSITIVE LOGITS
    lly
    0.52
    minist
    0.49
    gery
    0.49
    geoning
    0.48
    xual
    0.47
     perjury
    0.47
     parchment
    0.45
    puff
    0.44
    imity
    0.43
    arial
    0.43
    Activations Density 0.657%

    No Known Activations