INDEX

Explanations

instances of the word "await" and references to the variable "gamma"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-1.31

 Monfieur

-1.28

 myſelf

-1.20

NUMX

-1.17

$_"

-1.14

^(@)

-1.13

 itſelf

-1.10

ſelves

-1.09

 iſt

-1.09

leſs

-1.08

POSITIVE LOGITS

ры

0.86

cap

0.79

ur

0.76

urs

0.73

Cap

0.69

Cap

0.68

0.66

pri

0.65

0.64

Activations Density 0.162%

instances of the word "await" and references to the variable "gamma"

No Comments

No Known Activations