INDEX

Explanations

terms related to medical treatments and biochemistry

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تر

-0.48

´

-0.48

大山

-0.46

 оси

-0.45

 Marshall

-0.43

RTLE

-0.43

rav

-0.42

komend

-0.42

藤原

-0.42

 fluff

-0.42

POSITIVE LOGITS

 nahilalakip

0.83

FunctionFlags

0.80

 InputDecoration

0.79

Eth

0.78

eth

0.77

écnicas

0.77

tagHelperRunner

0.76

Eth

0.76

 concurrently

0.75

downe

0.72

Activations Density 2.732%

terms related to medical treatments and biochemistry

No Comments

No Known Activations