INDEX

Explanations

references to medical conditions and procedures, particularly involving tests and evaluations

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

/**

-0.69

ReactDOM

-0.56

tvguidetime

-0.56

dife

-0.55

 psycopg

-0.55

ษัท

-0.53

ظ

-0.53

 Svensson

-0.52

 mercan

-0.52

 مشارکت‌کنندگان

-0.51

POSITIVE LOGITS

 soften

0.74

 clarifying

0.68

 tighten

0.68

 softening

0.66

RTLD

0.65

Peel

0.65

 purify

0.65

IFYING

0.64

tifying

0.64

 flatten

0.63

Activations Density 3.224%

references to medical conditions and procedures, particularly involving tests and evaluations

No Comments

No Known Activations