INDEX

Explanations

evidence of comparisons or evaluations, particularly expressing opinions or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

StructEnd

-0.91

LookAnd

-0.84

ModelSerializer

-0.82

IUrlHelper

-0.80

########.

-0.77

 Baillargeon

-0.76

SharedDtor

-0.76

parsedMessage

-0.76

aarrggbb

-0.76

ChildScrollView

-0.73

POSITIVE LOGITS

 ujednoznacz

0.60

 means

0.58

is

0.54

isn

0.51

pro

0.50

0.47

 gives

0.45

 والت

0.45

 seems

0.44

<0x82>

0.44

Activations Density 0.485%

evidence of comparisons or evaluations, particularly expressing opinions or conditions

No Comments

No Known Activations