© 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. 17287
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations or political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to journalistic content and related terms

    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
     DU
    -0.83
     Bren
    -0.81
     DRAG
    -0.80
     brid
    -0.79
     DAC
    -0.76
     Ellen
    -0.76
     EAR
    -0.76
     CY
    -0.76
     Brid
    -0.75
     Compos
    -0.74
    POSITIVE LOGITS
    ist
    1.46
    ists
    1.36
    ism
    1.29
    IST
    1.20
    iste
    1.13
    istic
    1.08
    ista
    1.06
    ISM
    1.00
    ismo
    1.00
    istani
    0.98
    Activations Density 0.264%

    No Known Activations