INDEX

Explanations

phrases that discuss causation and conditions related to effects

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

ruppen

-0.45

 followed

-0.43

 seguida

-0.40

ArrowToggle

-0.40

retanto

-0.40

TabStop

-0.39

 kali

-0.39

ada

-0.39

本

-0.37

 held

-0.36

POSITIVE LOGITS

^(@)

0.91

ngdoc

0.89

Билгалдахарш

0.89

Efq

0.87

NUMX

0.84

ISupport

0.82

$_"

0.80

">:

0.78

 Reſ

0.77

 myſelf

0.77

Activations Density 0.499%

phrases that discuss causation and conditions related to effects

No Comments

No Known Activations