INDEX

Explanations

references to food experiences and dining

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

"for" or start of turn followed by "user"

np_acts-logits-general · gemini-2.0-flash

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

 '\\;'

-0.56

UserScript

-0.56

Filmographie

-0.53

URLException

-0.47

دانشنامهٔ

-0.46

 imprim

-0.45

AxisAlignment

-0.44

 Ridley

-0.44

Anlage

-0.43

ConstraintMaker

-0.43

POSITIVE LOGITS

 eating

1.14

eat

1.07

 eaten

1.04

 consumption

1.02

 devouring

1.00

 consuming

0.98

 consume

0.97

 devour

0.96

 devoured

0.94

 consumed

0.93

Activations Density 0.152%

references to food experiences and dining

"for" or start of turn followed by "user"

No Comments

No Known Activations