INDEX

Explanations

expressions of strong emphasis, particularly with the word "damn."

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

ins

-0.62

 overall

-0.58

sz

-0.54

off

-0.54

autoreleasepool

-0.54

 fair

-0.52

icoot

-0.52

sur

-0.52

emp

-0.52

try

-0.51

POSITIVE LOGITS

$_"

0.99

 attacker

0.95

fucker

0.89

 attacking

0.89

 attackers

0.88

 itſelf

0.81

 ويكيميديا

0.80

 reception

0.79

 pleaſure

0.78

Efq

0.78

Activations Density 0.112%

expressions of strong emphasis, particularly with the word "damn."

No Comments

No Known Activations