© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3339
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigation and observation

    oai_token-act-pair · gpt-3.5-turbo

    references to various entities and actions in diverse 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
     Peb
    -1.01
     Phone
    -0.84
     Pebble
    -0.83
     Pepper
    -0.82
    725
    -0.81
     Pom
    -0.81
    825
    -0.79
     Neb
    -0.78
     Ribbon
    -0.78
     Resp
    -0.77
    POSITIVE LOGITS
    uss
    0.94
     Davies
    0.88
    ix
    0.85
    AK
    0.83
     Ak
    0.81
    isation
    0.81
    aked
    0.78
    icz
    0.78
    akery
    0.78
     Hussain
    0.77
    Activations Density 0.332%

    No Known Activations