© 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. 10-RES-JB
    11. 13714
    Prev
    Next
    INDEX
    Explanations

    phrases related to audio content or podcasts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Listen" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subdu
    -0.64
     determination
    -0.59
    ]=
    -0.58
     membrane
    -0.58
     predetermined
    -0.58
     shroud
    -0.57
     bean
    -0.57
     bottleneck
    -0.55
     residue
    -0.55
    kin
    -0.55
    POSITIVE LOGITS
    ership
    1.08
    ings
    1.05
    ers
    1.02
     ·
    0.89
    ants
    0.84
     Now
    0.84
    ents
    0.83
    quartered
    0.82
    INGS
    0.79
     Below
    0.78
    Activations Density 0.041%

    No Known Activations