INDEX

Explanations

names of political figures and references to political events

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

:✨

-0.67

 ujednoznacz

-0.61

ISODE

-0.59

-0.57

)++;

-0.55

orec

-0.55

lified

-0.54

aktur

-0.53

QUAD

-0.53

pection

-0.53

POSITIVE LOGITS

and

0.64

ValueStyle

0.56

TagHelper

0.56

resave

0.55

 发表于

0.55

0.53

LookAnd

0.53

 protoimpl

0.53

 насељу

0.53

’

0.51

Activations Density 0.412%

names of political figures and references to political events

No Comments

No Known Activations