INDEX

Explanations

phrases that indicate connection or conjunction among ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ODD

-0.71

 itſelf

-0.69

 nakalista

-0.69

InputTagHelper

-0.65

 disambiguazione

-0.65

 Diſ

-0.65

ſelves

-0.65

 myſelf

-0.64

 ſever

-0.64

tonode

-0.63

POSITIVE LOGITS

 whose

0.76

who

0.60

whose

0.59

erals

0.51

 ModelExpression

0.50

ernalia

0.50

Whose

0.50

 cuyo

0.50

 represented

0.50

%;

0.49

Activations Density 0.321%

phrases that indicate connection or conjunction among ideas

No Comments

No Known Activations

phrases that indicate connection or conjunction among ideas

No Comments

No Known Activations