INDEX

Explanations

sequentially ordered lists or steps in a discussion or argument

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

expandindo

-0.62

abestanden

-0.61

########.

-0.61

期刊论文

-0.54

 مرئيه

-0.52

 المعيارى

-0.51

 casada

-0.51

+:+

-0.51

 estekak

-0.51

 windscreen

-0.50

POSITIVE LOGITS

Климат

0.75

ImageContext

0.69

unknownFields

0.66

 Combien

0.58

EnableWeb

0.57

 HttpHeaders

0.56

tso

0.55

Nuorodos

0.55

mesg

0.54

 HasFactory

0.54

Activations Density 0.297%

sequentially ordered lists or steps in a discussion or argument

No Comments

No Known Activations