INDEX

Explanations

the repeated use of the word "enough."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

er

-0.82

 Tala

-0.69

 Schol

-0.65

ṁ

-0.64

vari

-0.64

/**

-0.63

 objectMapper

-0.63

 Vari

-0.62

ﬂ

-0.62

 Castel

-0.61

POSITIVE LOGITS

elementary

0.95

 elementary

0.93

Elementary

0.89

 Elementary

0.87

ので

0.76

]--;

0.75

 Charlemagne

0.75

 Londra

0.74

ropra

0.73

 convencer

0.73

Activations Density 0.067%

the repeated use of the word "enough."

No Comments

No Known Activations