INDEX

Explanations

scholarly concepts related to hypotheses and academic discussions

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

 ſche

-0.70

 Shakspeare

-0.68

 Jefus

-0.67

 ſever

-0.67

 pleaſure

-0.64

 stiefel

-0.64

 ſmall

-0.63

 commerciaux

-0.61

 ſtate

-0.61

 physiologic

-0.61

POSITIVE LOGITS

 lenker

0.71

 scholars

0.68

 argued

0.68

 analyses

0.65

 argues

0.65

 JSTOR

0.65

contentLoaded

0.64

 Professors

0.63

JsonKey

0.63

 analyzes

0.62

Activations Density 0.392%

scholarly concepts related to hypotheses and academic discussions

No Comments

No Known Activations