INDEX

Explanations

variable declarations and definitions, especially related to looping structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

WithIOException

-0.86

AccessorTable

-0.73

,))

-0.70

évaluateur

-0.69

 territ

-0.66

 protoimpl

-0.66

})).

-0.64

 typename

-0.63

 *)__

-0.62

 Barbier

-0.62

POSITIVE LOGITS

InSection

0.66

 paramInt

0.66

rfloor

0.59

postIndex

0.57

 iVar

0.56

Tôi

0.55

imageshack

0.54

 IndexPath

0.54

genstein

0.53

elashes

0.52

Activations Density 0.072%

variable declarations and definitions, especially related to looping structures

No Comments

No Known Activations