INDEX

Explanations

phrases indicating durations or quantities related to time and experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 فريبيس

-0.91

 auffi

-0.84

 ")");

-0.84

ſelf

-0.83

 ſche

-0.80

')")

-0.79

 snippetHide

-0.79

 Roskov

-0.79

 houſe

-0.78

ſelves

-0.76

POSITIVE LOGITS

 maybe

1.72

 probably

1.51

maybe

1.47

 Maybe

1.33

 Probably

1.27

probably

1.25

Maybe

1.24

 perhaps

1.16

Probably

1.16

 about

1.14

Activations Density 0.272%

phrases indicating durations or quantities related to time and experience

No Comments

No Known Activations

phrases indicating durations or quantities related to time and experience

No Comments

No Known Activations