Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8197
    Prev
    Next
    INDEX
    Explanations

    possession or ownership references, such as "of their own"

    oai_token-act-pair · gpt-3.5-turbo

    sequences related to possession and ownership concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redacted
    -0.49
    ngth
    -0.48
    anwhile
    -0.48
     inval
    -0.48
    ources
    -0.47
    onest
    -0.46
     cropped
    -0.46
     pse
    -0.45
    reau
    -0.45
     Loaded
    -0.45
    POSITIVE LOGITS
     apocalypse
    0.53
     IPM
    0.51
     convergence
    0.49
     modification
    0.48
    venge
    0.47
    externalActionCode
    0.47
     ACTIONS
    0.47
    Council
    0.47
     renaissance
    0.47
     reconciliation
    0.46
    Activations Density 1.390%

    No Known Activations