INDEX

Explanations

references to comparisons and contrasts between two or more entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 AssemblyTitle

-0.84

 démocr

-0.66

+#+#

-0.65

 Roskov

-0.62

ThroughAttribute

-0.60

 Holman

-0.58

riction

-0.58

 Kinney

-0.57

:+:

-0.56

ringes

-0.56

POSITIVE LOGITS

 davon

0.58

これも

0.58

 chúng

0.55

jenige

0.55

الإنجليزية

0.54

 could

0.54

 antaranya

0.52

ModelAndView

0.51

 would

0.51

had

0.51

Activations Density 0.357%

references to comparisons and contrasts between two or more entities

No Comments

No Known Activations