© 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. 21457
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the"

    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
    itus
    -0.68
     wondered
    -0.67
    pointers
    -0.67
    oko
    -0.66
    worms
    -0.66
    ben
    -0.65
    iva
    -0.64
     nods
    -0.62
    abilia
    -0.62
    igans
    -0.62
    POSITIVE LOGITS
     vicinity
    1.36
     absence
    1.27
     context
    1.24
     guise
    1.19
     presence
    1.16
     midst
    1.10
     form
    1.04
     manner
    1.02
     meantime
    1.02
     simplest
    1.00
    Activations Density 0.219%

    No Known Activations