INDEX

Explanations

references to time durations

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

.•

-0.82

 AssemblyCompany

-0.76

ApplicationTests

-0.72

 aanbod

-0.71

 réglementation

-0.71

dyti

-0.71

~•

-0.70

Bibliographie

-0.70

 Bioaccumulative

-0.70

 NSCoder

-0.69

POSITIVE LOGITS

 minutes

2.04

 Minutes

1.84

 minute

1.75

minutes

1.68

Minutes

1.66

 MINUTES

1.64

 MINUTE

1.63

 Minute

1.59

minute

1.51

Minute

1.51

Activations Density 0.046%

references to time durations

No Comments

No Known Activations