INDEX

Explanations

places and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

ChildScrollView

-0.93

ThroughAttribute

-0.84

__':

-0.82

initializeApp

-0.80

Życiorys

-0.79

ruptedException

-0.77

 GlobalKey

-0.77

 joaat

-0.76

iostream

-0.74

RectangleBorder

-0.74

POSITIVE LOGITS

↵

1.17

0.91

0.90

0.89

<eos>

0.87

0.86

0.85

0.83

0.82

Activations Density 0.059%

places and locations

No Comments

No Known Activations