INDEX

Explanations

statements about personal experiences and reflections involving reading and discussing various topics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 habet

-0.80

 pleaſure

-0.76

 ſtate

-0.76

 houſe

-0.74

 greateſt

-0.72

 beſt

-0.72

 itſelf

-0.72

 purpoſe

-0.71

 juſ

-0.70

 Majefty

-0.69

POSITIVE LOGITS

 recently

0.81

 reminded

0.72

 yesterday

0.71

recently

0.69

最近

0.67

 kürzlich

0.65

 lately

0.64

Recently

0.62

 disambiguazione

0.60

先日

0.58

Activations Density 0.432%

statements about personal experiences and reflections involving reading and discussing various topics

No Comments

No Known Activations