INDEX

Explanations

terms related to digestion and digestive processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 kasarigan

-0.50

 Protective

-0.43

 constitutional

-0.39

 protective

-0.39

Protective

-0.39

TRAILING

-0.39

 Threat

-0.38

IBOutlet

-0.38

 Threatened

-0.37

threat

-0.37

POSITIVE LOGITS

 digest

0.71

消化

0.66

 digestion

0.66

 Digestion

0.64

 digested

0.61

digest

0.58

Digest

0.56

 Digest

0.55

 digestive

0.54

 DIGEST

0.50

Activations Density 0.365%

terms related to digestion and digestive processes

No Comments

No Known Activations