INDEX

Explanations

references to notable individuals and their achievements

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

 sogget

-0.57

AndEndTag

-0.55

 Autorizaciones

-0.53

każ

-0.47

TacToe

-0.47

 CURIAM

-0.47

ัง

-0.44

 Assyrian

-0.43

aarrggbb

-0.43

 mijne

-0.43

POSITIVE LOGITS

WriteBarrier

0.74

 jsPsych

0.66

mybatisplus

0.64

cycline

0.64

StackSize

0.63

migrationBuilder

0.61

Cyfarwyddwr

0.60

出版年

0.60

 跳转至

0.59

曖昧さ回避

0.59

Activations Density 0.377%

references to notable individuals and their achievements

No Comments

No Known Activations