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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12870
    Prev
    Next
    INDEX
    Explanations

    names related to specific geographical locations, potentially indicating a focus on place-related entities

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms related to elements of popular music or bands

    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
    urable
    -0.76
    enance
    -0.74
     partic
    -0.74
     allowable
    -0.74
     divid
    -0.72
     epid
    -0.72
     coron
    -0.69
     mas
    -0.69
     dil
    -0.68
     antip
    -0.67
    POSITIVE LOGITS
     Bowl
    1.07
     Creek
    1.04
     Springs
    1.00
     Hearts
    1.00
     Hands
    0.96
    byte
    0.96
     Horse
    0.96
    finger
    0.95
    hawk
    0.94
     Boy
    0.94
    Activations Density 0.166%

    No Known Activations