INDEX

Explanations

references to collections in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 atve

-0.67

 komer

-0.63

elds

-0.58

afety

-0.55

 actually

-0.55

όμε

-0.55

hütte

-0.54

txt

-0.54

 FOLLOWING

-0.54

 ACTUALLY

-0.53

POSITIVE LOGITS

Collections

2.46

 Collections

1.51

 collections

1.15

collections

1.08

 Collection

0.83

collection

0.82

Collection

0.81

InputBorder

0.79

 collection

0.79

</thead>

0.78

Activations Density 0.010%

references to collections in programming contexts

No Comments

No Known Activations