INDEX

Explanations

symbols and notations commonly associated with mathematical expressions, particularly involving derivatives and transformations of functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

googleapis

-0.68

 getLayout

-0.65

дакти

-0.63

 कैसी

-0.63

dora

-0.61

")[

-0.61

mongo

-0.59

SetColor

-0.59

idro

-0.59

ADORA

-0.59

POSITIVE LOGITS

prime

1.17

′

0.95

aarrggbb

0.81

FailureListener

0.79

ApiProperty

0.79

PRIME

0.78

strptime

0.77

 sympy

0.74

-'

0.73

′,

0.72

Activations Density 0.198%

symbols and notations commonly associated with mathematical expressions, particularly involving derivatives and transformations of functions

No Comments

No Known Activations