INDEX

Explanations

phrases emphasizing conditions or qualifications related to various contexts

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

"For" followed by a word indicating purpose or instance

np_acts-logits-general · gemini-2.0-flash

for each, for example

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

AsUp

-0.74

URLException

-0.71

ResumeLayout

-0.67

principalColumn

-0.65

تفصیلات

-0.60

Élet

-0.59

ImageContext

-0.56

 MainAxisSize

-0.55

 calculées

-0.52

using

-0.52

POSITIVE LOGITS

 convenience

0.83

abestanden

0.75

 easier

0.75

 ease

0.74

 simplicity

0.74

 each

0.72

convenience

0.66

 gemak

0.65

 facilit

0.60

 Easier

0.59

Activations Density 0.431%

phrases emphasizing conditions or qualifications related to various contexts

"For" followed by a word indicating purpose or instance

for each, for example

No Comments

No Known Activations