INDEX

Explanations

references to the first-person perspective

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Theſe

-0.89

 Beſ

-0.83

 Cuen

-0.77

 wach

-0.76

 εμπ

-0.76

 abond

-0.74

 CRACK

-0.72

Jeografia

-0.72

thenia

-0.72

 tork

-0.71

POSITIVE LOGITS

1.74

1.57

1.10

iI

1.00

я

0.94

IOUtils

0.93

pI

0.92

𝗜

0.90

आई

0.88

aI

0.87

Activations Density 0.125%

references to the first-person perspective

No Comments

No Known Activations