INDEX

Explanations

references to services and service-related operations in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

بعض

-0.43

 eens

-0.41

nesia

-0.41

 rearranged

-0.41

'__

-0.41

AILED

-0.41

vla

-0.41

 beberapa

-0.40

broek

-0.40

missao

-0.40

POSITIVE LOGITS

PMailer

1.00

service

0.85



0.85

 &___

0.82

 LUMP

0.80

stdc

0.79

ImageContext

0.77

脚注の使い方

0.76

SourceChecksum

0.75

 protoimpl

0.75

Activations Density 0.150%

references to services and service-related operations in code

No Comments

No Known Activations