INDEX

Explanations

phrases reflecting possibilities and the concept of imagining different futures

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

following "can", "never", or "to"

np_acts-logits-general · gemini-2.0-flash

can imagine

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Izvori

-0.83

IsContent

-0.77

Efq

-0.77

 оригіналу

-0.72

AddTagHelper

-0.72

 uſe

-0.68

 betweenstory

-0.68

mybatisplus

-0.68

">—

-0.67

género

-0.66

POSITIVE LOGITS

 imagine

2.30

 imagining

1.99

 imagined

1.97

imagine

1.89

 Imagine

1.89

 imagines

1.86

Imagine

1.78

 imaginar

1.78

 IMAG

1.75

 imagin

1.73

Activations Density 0.220%

phrases reflecting possibilities and the concept of imagining different futures

following "can", "never", or "to"

can imagine

No Comments

No Known Activations