INDEX

Explanations

references to podcasts and podcasting

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

 Anam

-0.75

 Sver

-0.74

ніципалі

-0.73

 Brice

-0.73

 Ganga

-0.69

declarations

-0.68

__).

-0.68

たまた

-0.68

umman

-0.68

rmızı

-0.68

POSITIVE LOGITS

pod

1.90

Pod

1.87

 podcast

1.86

Pod

1.74

 pods

1.74

 podcasts

1.70

pod

1.63

 Podcast

1.56

 Pods

1.51

podcast

1.51

Activations Density 0.037%

references to podcasts and podcasting

No Comments

No Known Activations