INDEX

Explanations

strong affirmative expressions of agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

PYX

-0.72

 arabe

-0.63

 Henson

-0.62

？』

-0.62

 Guen

-0.62

ModelForm

-0.61

 financières

-0.60

Selen

-0.60

Hen

-0.58

Continu

-0.58

POSITIVE LOGITS

 Absol

1.17

UTELY

0.89

Abs

0.89

 ―――――

0.88

Jacqueline

0.88

getAbsolutePath

0.88

queline

0.88

 Szcz

0.83

 absol

0.83

 cobalt

0.82

Activations Density 0.051%

strong affirmative expressions of agreement

No Comments

No Known Activations