INDEX

Explanations

references to specific awards in television and film

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

aarrggbb

-0.72

 estimés

-0.71

 trouw

-0.69

onAttach

-0.68

 Majefty

-0.65

beforeEach

-0.65

parsedMessage

-0.65

GraphicsUnit

-0.64

 Dominus

-0.64

 distanciation

-0.64

POSITIVE LOGITS

red

1.75

ded

1.68

sed

1.66

ged

1.57

ced

1.55

zed

1.49

bed

1.48

ted

1.44

RED

1.43

led

1.43

Activations Density 0.111%

references to specific awards in television and film

No Comments

No Known Activations