INDEX

Explanations

instances of lists or enumerations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 CreateTagHelper

-0.75

 deose

-0.65

 stesse

-0.61

 îna

-0.59

 servici

-0.58

 nymphs

-0.57

 medesimo

-0.56

 giud

-0.55

The

-0.54

 cantit

-0.54

POSITIVE LOGITS

non

0.99

 high

0.88

low

0.85

^(@)

0.82

}}],

0.82

SequentialGroup

0.80

SOUNDBITE

0.78

expandindo

0.78

 виправивши

0.78

?>/

0.78

Activations Density 0.086%

instances of lists or enumerations

No Comments

No Known Activations