© 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. 20422
    Prev
    Next
    INDEX
    Explanations

    short phrases ending with a comma

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating excessive or overwhelming amounts of something

    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
    erick
    -0.63
    erd
    -0.61
    eret
    -0.61
    ickers
    -0.60
    wyn
    -0.60
    uring
    -0.60
    agram
    -0.58
    xt
    -0.58
    icial
    -0.57
    ãĤĮ
    -0.54
    POSITIVE LOGITS
    except
    1.49
     including
    1.48
     regardless
    1.46
     except
    1.42
     irrespective
    1.40
     Including
    1.38
    including
    1.37
     INCLUD
    1.24
     anytime
    1.22
    excluding
    1.12
    Activations Density 0.262%

    No Known Activations