INDEX

Explanations

elements related to decoding and formatting operations in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

didSet

-0.76

opsida

-0.64

Subviews

-0.63

Mil

-0.62

httphttps

-0.61

̀u

-0.60

AndFlush

-0.60

újo

-0.58

wsdl

-0.58

orescence

-0.58

POSITIVE LOGITS

Efq

1.19

 ſche

1.17

ſelf

1.16

 houſe

1.15

 Monfieur

1.12

ſy

1.06

 purpoſe

1.02

unner

1.02

 pleaſure

1.01

 Beller

1.00

Activations Density 0.593%

elements related to decoding and formatting operations in programming

No Comments

No Known Activations