INDEX

Explanations

equal signs in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

—

-0.88

-0.82

 nonatomic

-0.80

 Duran

-0.78

->

-0.78

±

-0.78

–

-0.78

<<

-0.76

-0.74

·

-0.74

POSITIVE LOGITS

0.96

 étoit

0.89

 Sixteenth

0.85

 doré

0.85

 piú

0.85

 Rijks

0.85

 Inscrivez

0.84

 dedans

0.84

 tremp

0.84

 Becher

0.83

Activations Density 0.316%

equal signs in the document

No Comments

No Known Activations