INDEX

Explanations

programming terminology and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

RectangleBorder

-1.06

 Compañ

-0.85

 ―――――

-0.84

 itſelf

-0.82

 ་་

-0.81

存于互联网档案馆

-0.80

ſelf

-0.80

ſelves

-0.79

 themſelves

-0.78

theless

-0.77

POSITIVE LOGITS

InSection

0.83

TypedDataSet

0.68

execSQL

0.62

 oprot

0.58

 "..\..\..\

0.55

 suivantes

0.55

JsonInclude

0.54

Напомним

0.53

WHEREAS

0.53

pushd

0.52

Activations Density 0.719%

programming terminology and structure

No Comments

No Known Activations