INDEX

Explanations

occurrences of the word "on."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SpringBootTest

-0.78

">//

-0.78

tvguidetime

-0.75

 <<<<<<<<<<<<<<

-0.72

Cyfeiriadau

-0.67

脚注の使い方

-0.67

berdayakan

-0.65

webf

-0.65

tagHelperRunner

-0.64

ällor

-0.64

POSITIVE LOGITS

клопе

0.64

 road

0.59

Buk

0.56

 springfox

0.56

bukkit

0.54

 witness

0.53

go

0.52

ExecuteReader

0.51

 sacco

0.51

 goes

0.51

Activations Density 0.052%

occurrences of the word "on."

No Comments

No Known Activations