© 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. 4-RES-JB
    11. 17064
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or association

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference groups of people and their experiences or conditions

    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
     Courier
    -0.65
     roundup
    -0.61
     Schr
    -0.60
    \/\/
    -0.60
    Ted
    -0.59
     Rescue
    -0.58
    balls
    -0.58
    OLOG
    -0.57
     Giles
    -0.57
     Annie
    -0.57
    POSITIVE LOGITS
    mol
    0.85
    kie
    0.82
    iw
    0.73
    rame
    0.72
    cients
    0.72
     contemplate
    0.72
    esta
    0.71
    iled
    0.71
    iris
    0.68
    atives
    0.68
    Activations Density 0.142%

    No Known Activations