INDEX

Explanations

references to external links and documentation sections

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

########.

-0.85

 المعيارى

-0.75

 فريبيس

-0.69

rollment

-0.67

 ujednoznacz

-0.63

లాలు

-0.62

JspWriter

-0.62

Біографія

-0.61

 StatusCode

-0.61

ighborhood

-0.61

POSITIVE LOGITS

TagMode

0.97

see

0.85

matchCondition

0.73

bkz

0.65

AnchorStyles

0.61

τία

0.61

?";

0.58

 https

0.56

SEE

0.55

satunya

0.54

Activations Density 0.027%

references to external links and documentation sections

No Comments

No Known Activations