INDEX

Explanations

references to spontaneous actions or events

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

 morire

-0.55

 zijne

-0.51

ProgressHUD

-0.51

 Lode

-0.51

Married

-0.49

 Married

-0.49

fő

-0.48

 palsu

-0.48

 married

-0.47

 sposa

-0.47

POSITIVE LOGITS

 spont

1.01

 spontan

0.99

 spontaneously

0.98

 spontaneous

0.94

ontaneous

0.87

 espont

0.84

 Spontaneous

0.81

 unsolicited

0.76

勝手に

0.73

 tự

0.72

Activations Density 0.615%

references to spontaneous actions or events

No Comments

No Known Activations