INDEX

Explanations

positive emotional responses and descriptive adjectives in reviews or reflections

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

Follows "was" or past tense

np_acts-logits-general · gemini-2.0-flash

was followed by adjectives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 currently

-0.96

currently

-0.94

now

-0.93

 presently

-0.91

 nowadays

-0.90

 attualmente

-0.86

 obecnie

-0.80

 actuellement

-0.79

 atualmente

-0.78

 derzeit

-0.77

POSITIVE LOGITS

 previously

0.79

 originally

0.78

Wasn

0.78

 Wasn

0.76

 originalmente

0.74

 ayer

0.74

 initially

0.73

 autrefois

0.69

 wasn

0.69

ThroughAttribute

0.69

Activations Density 0.483%

positive emotional responses and descriptive adjectives in reviews or reflections

Follows "was" or past tense

was followed by adjectives

No Comments

No Known Activations