INDEX

Explanations

the prefix "pro" in various contexts

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

SourceChecksum

-0.77

fjspx

-0.74

ValueStyle

-0.73

帖最后由

-0.69

 consulté

-0.68

migrationBuilder

-0.68

ंदीखरीदारी

-0.66

stdc

-0.64

 مُعرِّف

-0.64

Referencer

-0.64

POSITIVE LOGITS

pro

3.81

Pro

3.58

PRO

3.52

PRO

3.51

Pro

3.44

pro

3.42

プロ

2.40

pros

2.17

 Pros

2.16

про

2.15

Activations Density 0.148%

the prefix "pro" in various contexts

No Comments

No Known Activations