INDEX

Explanations

mentions of shops and online retail experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 auffi

-1.06

 myſelf

-1.02

 pleaſure

-0.96

 Theſe

-0.92

 ſche

-0.91

 ainfi

-0.91

 iſt

-0.90

 ſtate

-0.90

 eſt

-0.90

 greateſt

-0.88

POSITIVE LOGITS

 shop

0.76

shop

0.75

 Shop

0.70

Shop

0.67

ACCESS

0.62

 room

0.62

hop

0.57

exit

0.56

↵↵

0.56

Activations Density 0.085%

mentions of shops and online retail experiences

No Comments

No Known Activations