INDEX

Explanations

expressions of liking or affection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Asher

-0.75

èvre

-0.72

 Hernandez

-0.71

 Pennington

-0.68

 Berman

-0.68

 Crowe

-0.67

<h6>

-0.65

шель

-0.63

codegen

-0.63

din

-0.62

POSITIVE LOGITS

 liked

0.96

 Liked

0.92

dislike

0.88

 Likes

0.86

Likes

0.84

 gusta

0.84

Lik

0.81

 dislike

0.81

 liking

0.78

👍👍

0.77

Activations Density 0.049%

expressions of liking or affection

No Comments

No Known Activations