INDEX

Explanations

phrases indicating legal or procedural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

-0.81

 myſelf

-0.81

 تضيفلها

-0.77

 themſelves

-0.77

AndEndTag

-0.74

 ddelweddau

-0.74

 himſelf

-0.73

 itſelf

-0.72

 Majefty

-0.69

 Monfieur

-0.69

POSITIVE LOGITS

 which

1.39

which

1.00

 Which

1.00

 whose

0.93

 WHICH

0.90

Which

0.87

 whom

0.75

cui

0.72

whose

0.71

 whereby

0.69

Activations Density 0.146%

phrases indicating legal or procedural contexts

No Comments

No Known Activations