INDEX

Explanations

terms related to medical conditions, treatments, and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

IBAction

-0.32

clear

-0.29

very

-0.29

清

-0.29

 señalado

-0.28

text

-0.28

fter

-0.28

 clear

-0.28

 confiar

-0.28

der

-0.27

POSITIVE LOGITS

 Roskov

0.68

ThroughAttribute

0.61

UnusedPrivate

0.60

 kasarigan

0.59

 >=",

0.58

TagMode

0.57

 ComVisible

0.57

 ControllerBase

0.56

WriteTagHelper

0.56

enderror

0.55

Activations Density 0.779%

terms related to medical conditions, treatments, and their effects

No Comments

No Known Activations