INDEX

Explanations

expressions of similarity or resemblance

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

 myſelf

-0.96

 purpoſe

-0.93

 Theſe

-0.88

 raiſ

-0.85

 Anſ

-0.84

Efq

-0.84

 Majefty

-0.84

 cauſe

-0.84

 themſelves

-0.83

 whoſe

-0.83

POSITIVE LOGITS

the

0.77

WriteTagHelper

0.69

 like

0.64

 onCreateView

0.58

 Like

0.58

0.57

 those

0.55

produkte

0.54

 כמו

0.51

INCREF

0.51

Activations Density 0.388%

expressions of similarity or resemblance

No Comments

No Known Activations