INDEX

Explanations

references to duration in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

?\\

-0.81

.\\

-0.81

iibo

-0.78

).\\

-0.78

()]);

-0.73

]:

-0.72

 userModel

-0.72

[];

-0.71

"]));

-0.71

INSEE

-0.70

POSITIVE LOGITS

 duration

2.28

duration

2.16

 Duration

2.02

Duration

1.93

 durations

1.86

DURATION

1.80

DUR

1.36

 durée

1.36

setDuration

1.30

DUR

1.13

Activations Density 0.071%

references to duration in various contexts

No Comments

No Known Activations