INDEX

Explanations

code-related concepts pertaining to data types and their memory representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 htons

-0.61

出版年

-0.61

EndContext

-0.56

IUrlHelper

-0.55

usermodel

-0.54

 BoxFit

-0.53

awtextra

-0.53

AndEndTag

-0.51

Sortie

-0.51

 незавершена

-0.50

POSITIVE LOGITS

 long

1.74

long

1.67

Long

1.50

 Long

1.47

 LONG

1.28

LONG

1.17

setLong

1.04

getLong

1.03

 longs

1.03

 lång

1.00

Activations Density 0.430%

code-related concepts pertaining to data types and their memory representation

No Comments

No Known Activations

code-related concepts pertaining to data types and their memory representation

No Comments

No Known Activations