INDEX

Explanations

references to military or armed groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

cstring

-0.55

omer

-0.50

 mañana

-0.46

òng

-0.46

하

-0.46

weep

-0.44

 Term

-0.44

old

-0.44

ถ

-0.43

Mit

-0.43

POSITIVE LOGITS

 CURIAM

0.89

StoryboardSegue

0.89

 obstacle

0.83

+:+

0.82

WithIOException

0.80

StructEnd

0.78

 Obstacle

0.76

EReference

0.74

 незавершена

0.74

 obstacles

0.73

Activations Density 0.093%

references to military or armed groups

No Comments

No Known Activations