INDEX

Explanations

phrases and concepts related to research findings and reports

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

aimerais

-0.45

complexType

-0.45

ver

-0.44

<eos>

-0.40

 selve

-0.39

勇

-0.39

τό

-0.39

-0.38

 copy

-0.38

 пере

-0.38

POSITIVE LOGITS

 '\\;'

0.93

NUMX

0.87

niająca

0.79

AddHtmlAttribute

0.77

 ―――――

0.76

Efq

0.74

(!__

0.70

ChildScrollView

0.70

$_"

0.70

moiselle

0.69

Activations Density 0.502%

phrases and concepts related to research findings and reports

No Comments

No Known Activations