INDEX

Explanations

phrases indicating personal limitations or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Datuak

-0.81

 beginnetje

-0.74

 transfieras

-0.74

 kaarangay

-0.72

তথ্যসূত্র

-0.69

EndContext

-0.68

انيف

-0.66

 AssemblyCulture

-0.66

Vidite

-0.65

✨:

-0.65

POSITIVE LOGITS

 they

0.66

we

0.51

thenReturn

0.48

нская

0.47

 there

0.46

she

0.45

 trọng

0.45

│

0.44

rary

0.43

افظ

0.42

Activations Density 0.045%

phrases indicating personal limitations or experiences

No Comments

No Known Activations