INDEX

Explanations

phrases related to reading, sharing, and engaging with content

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

Followed by function words

np_acts-logits-general · gemini-2.0-flash

instructions and examples

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

exitRule

-0.48

RectangleBorder

-0.48

 defaultstate

-0.46

migrationBuilder

-0.45

Билгалдахарш

-0.43

complexType

-0.43

oprecipitation

-0.42

 finition

-0.41

tazione

-0.41

Eksteraj

-0.40

POSITIVE LOGITS

 aviation

1.05

 gaming

0.91

 automotive

0.88

aviation

0.86

 football

0.85

 motorsport

0.85

 rugby

0.83

 horticultural

0.83

 sports

0.82

 gardening

0.81

Activations Density 1.307%

phrases related to reading, sharing, and engaging with content

Followed by function words

instructions and examples

No Comments

No Known Activations