INDEX

Explanations

numeric values used in mathematical or computational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

TextUtils

-0.52

 pair

-0.49

pair

-0.49

простра

-0.48

 pairs

-0.48

 htons

-0.46

 rosemary

-0.45

entor

-0.43

 FetchType

-0.43

lename

-0.43

POSITIVE LOGITS

 Paglinawan

0.91

yntaxException

0.83

SourceChecksum

0.79

 POWERS

0.61

 '\\;'

0.60

UpInside

0.60

RenderAtEndOf

0.59

 powers

0.58

 Exponential

0.57

 للاسماء

0.56

Activations Density 2.158%

numeric values used in mathematical or computational contexts

No Comments

No Known Activations