INDEX

Explanations

contraction forms of words related to negation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

expandindo

-1.09

 ModelExpression

-0.97

 виправивши

-0.95

 Мексичка

-0.94

IUrlHelper

-0.94

 transfieras

-0.88

 AspNetCore

-0.86

 Савезне

-0.86

 صوتيه

-0.83

oredCriteria

-0.81

POSITIVE LOGITS

 getting

0.70

…

0.66

 things

0.60

 just

0.58

“

0.58

put

0.57

 truly

0.56

 anything

0.55

‘

0.54

 what

0.54

Activations Density 0.243%

contraction forms of words related to negation

No Comments

No Known Activations