INDEX

Explanations

dialogue exchanges involving questions and authoritative responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 plus

-0.48

 insuffisamment

-0.47

elif

-0.45

Plus

-0.45

ίων

-0.45

ocarp

-0.45

除

-0.45

seteq

-0.44

habits

-0.44

 numbers

-0.44

POSITIVE LOGITS

 replied

1.02

 nodding

0.99

 laughed

0.97

 smiled

0.96

 nodded

0.95

 chuckled

0.94

 whispered

0.93

 Hearing

0.91

 pointing

0.89

 giggled

0.89

Activations Density 0.244%

dialogue exchanges involving questions and authoritative responses

No Comments

No Known Activations