INDEX

Explanations

connections and relationships between concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Lainnya

-0.57

 lainnya

-0.57

boxylic

-0.56

همچنین

-0.56

possibly

-0.55

 possibly

-0.55

wiad

-0.54

RegressionTest

-0.54

 defStyleAttr

-0.53

 satunya

-0.53

POSITIVE LOGITS

 between

0.74

0.72

 между

0.70

 sexes

0.68

หว่าง

0.66

ValueGenerated

0.65

 antara

0.63

Rujuakan

0.62

 Between

0.61

IBOutlet

0.61

Activations Density 0.353%

connections and relationships between concepts or entities

No Comments

No Known Activations