INDEX

Explanations

references to various forms of biological and viral classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

CardHeader

-0.87

 سكانية

-0.79

Berikut

-0.79

க்கும்

-0.78

 Boch

-0.78

المشاركات

-0.76

ydı

-0.74

orenje

-0.74

pendente

-0.72

zące

-0.72

POSITIVE LOGITS

ly

0.92

theless

0.90

teen

0.85

 perſon

0.85

 pleaſure

0.84

 diſt

0.81

 itſelf

0.81

 Reſ

0.81

 auffi

0.81

 figliu

0.80

Activations Density 1.522%

references to various forms of biological and viral classification

No Comments

No Known Activations