INDEX

Explanations

references to specific items or entities, particularly products or features

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

followed by height or age

np_acts-logits-general · gemini-2.0-flash

positive sentiment

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 GenerationType

-0.66

‚¬

-0.60

σεων

-0.59

 nahilalakip

-0.59

zugehen

-0.56

InputBorder

-0.55

ibid

-0.55

 كومونز

-0.54

otesi

-0.54

=$?

-0.52

POSITIVE LOGITS

 Excellent

0.93

Excellent

0.91

Very

0.89

Amazing

0.84

 Very

0.83

 Excelente

0.82

 Amazing

0.81

 excellent

0.81

Fantastic

0.79

 amazing

0.77

Activations Density 0.030%

references to specific items or entities, particularly products or features

followed by height or age

positive sentiment

No Comments

No Known Activations