INDEX

Explanations

expressions of apology or regret

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

GHIJKLM

-0.92

Hauptartikel

-0.89

 समीक्षक

-0.88

ientôt

-0.86

styleType

-0.85

awtextra

-0.83

 FetchType

-0.82

pperware

-0.82

 חיצוניים

-0.79

 autorytatywna

-0.78

POSITIVE LOGITS

 apologise

1.09

 apologised

1.09

 apology

1.08

 sorry

1.06

 SORRY

1.02

 apologies

1.02

 Sorry

0.98

Sorry

0.95

 apologize

0.90

 apologizing

0.89

Activations Density 0.058%

expressions of apology or regret

No Comments

No Known Activations