INDEX

Explanations

negative expressions or negations in statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

XXIII

-0.62

 pleaſure

-0.60

 fevere

-0.58

 ricardo

-0.55

 ſever

-0.54

 Sardinia

-0.53

PIB

-0.53

KGB

-0.53

進む

-0.52

 Hildebrand

-0.52

POSITIVE LOGITS

ValueStyle

1.16

 necessarily

1.13

yet

1.11

 חיצוניים

1.09

AddTagHelper

1.07

yet

1.00

 Normdatei

0.99

(!__

0.98

MigrationBuilder

0.94

 propOrder

0.93

Activations Density 0.510%

negative expressions or negations in statements

No Comments

No Known Activations