INDEX

Explanations

phrases indicating a basis for reasoning or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ⓧ

-0.74

TagHelper

-0.61

 accesorios

-0.60

bravo

-0.59

 MonoBehaviour

-0.56

 utafitiHapana

-0.56

JvmStatic

-0.55

 acessórios

-0.54

Tikang

-0.53

archiviato

-0.52

POSITIVE LOGITS

Based

0.72

 beruht

0.71

 Based

0.69

">/

0.68

BASED

0.67

dasarkan

0.67

 tiré

0.67

基于

0.66

に基

0.65

 based

0.64

Activations Density 0.358%

phrases indicating a basis for reasoning or conclusions

No Comments

No Known Activations