INDEX

Explanations

references to academic citations or footnotes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

<eos>

-0.42

Pert

-0.42

++]

-0.41

Per

-0.41

からです

-0.40

_("

-0.40

 Photocase

-0.40

sel

-0.39

ことにしました

-0.39

POSITIVE LOGITS

 kasarigan

1.18

 дописавши

1.08

protoimpl

1.02

 '\\;'

0.98

PerformLayout

0.92

ContentAsync

0.89

QMetaType

0.88

__":

0.87

adpleegd

0.87

出版年

0.86

Activations Density 0.583%

references to academic citations or footnotes

No Comments

No Known Activations