INDEX

Explanations

terms related to audience engagement and participation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 utafitiHapana

-0.94

 فريبيس

-0.87

########.

-0.80

AndEndTag

-0.75

 Numerade

-0.73

SharedCtor

-0.70

 mourut

-0.69

 mergeFrom

-0.69

 خارجية

-0.69

 صوتيه

-0.68

POSITIVE LOGITS

 readers

0.77

 fans

0.69

大家

0.65

 viewers

0.61

Readers

0.61

 Fans

0.58

 familiar

0.57

readers

0.56

 anyone

0.56

Fans

0.56

Activations Density 0.228%

terms related to audience engagement and participation

No Comments

No Known Activations