INDEX

Explanations

instances of the word "switch."

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

Попис

-0.56

uxxxx

-0.56

 kaarangay

-0.53

neté

-0.53

μφ

-0.51

TAINMENT

-0.49

rungsseite

-0.48

 Concord

-0.48

المشاركات

-0.48

 referenties

-0.47

POSITIVE LOGITS

Switch

0.98

 switch

0.92

 Switch

0.91

 Switching

0.89

 switched

0.86

 switching

0.80

 SWITCH

0.77

Switching

0.77

SWITCH

0.77

switch

0.77

Activations Density 0.238%

instances of the word "switch."

No Comments

No Known Activations