© 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. 11446
    Prev
    Next
    INDEX
    Explanations

    instances of sentences that contain the word "haven't"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "haven" in various contexts

    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
     manifests
    -0.66
    upp
    -0.64
    alach
    -0.60
    cision
    -0.60
     Dise
    -0.59
    dimensional
    -0.58
     Dial
    -0.57
     Kills
    -0.57
    BD
    -0.57
    ermanent
    -0.57
    POSITIVE LOGITS
    't
    1.17
    ajor
    0.98
    geon
    0.94
    ited
    0.90
    vier
    0.86
     Been
    0.85
    nas
    0.82
    nell
    0.81
    ãĤ©
    0.80
    ned
    0.79
    Activations Density 0.008%

    No Known Activations