INDEX

Explanations

occurrences of the variable "i" in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 ویکی‌پدی

-0.71

LookAnd

-0.65

 disambiguazione

-0.61

 estekak

-0.52

TagMode

-0.51

 Meksiku

-0.50

 nonUne

-0.50

AntiForgeryToken

-0.50

 متحده

-0.50

↵↵

-0.49

POSITIVE LOGITS

AxisAlignment

0.91

)");

0.88

 MainAxisSize

0.80

NUMX

0.78

"],

0.76

complexContent

0.75

 XNUMX

0.75

PreExecute

0.74

abatic

0.73

 TextInputType

0.72

Activations Density 0.012%

occurrences of the variable "i" in code snippets

No Comments

No Known Activations