INDEX

Explanations

dates and time-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

^^^^^^^^

-0.90

 Psyche

-0.84

 Tartar

-0.81

\}\\

-0.81

 XNUMX

-0.81

étés

-0.81

>>>>>>>>

-0.79

Okey

-0.78

 Anam

-0.78

'>"

-0.77

POSITIVE LOGITS

Fig

0.82

httphttps

0.82

Aug

0.82

Nov

0.82

Fig

0.79

 Atty

0.78

Feb

0.78

Oct

0.77

Jan

0.77

Figs

0.74

Activations Density 0.147%

dates and time-related information

No Comments

No Known Activations