INDEX

Explanations

references to technical or programming elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

"))

-0.55

 Cliquez

-0.55

躇

-0.55

MENAFN

-0.53

Cap

-0.51

ividual

-0.50

മ്

-0.49

 Diſ

-0.49

AtIndexPath

-0.49

 ARRAY

-0.48

POSITIVE LOGITS

AndEndTag

0.88

rawDesc

0.82

WriteTagHelper

0.81

RectangleBorder

0.78

CppCodeGen

0.73

 beginnetje

0.73

0.72

PerformLayout

0.70

anadas

0.70

IsMutable

0.69

Activations Density 0.721%

references to technical or programming elements

No Comments

No Known Activations