INDEX

Explanations

mentions of television-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-1.41

 itſelf

-1.38

 Anſ

-1.22

 Monfieur

-1.19

 Theſe

-1.19

 ſeveral

-1.17

 Jefus

-1.16

 themſelves

-1.13

Eſ

-1.12

 himſelf

-1.12

POSITIVE LOGITS

TV

1.09

TV

0.72

 television

0.70

Hel

0.67

د

0.65

<eos>

0.63

0.60

0.59

 televisión

0.56

Activations Density 0.235%

mentions of television-related content

No Comments

No Known Activations