INDEX

Explanations

specific medical abbreviations and related terms

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

er

-0.84

-0.80

PickerController

-0.78

InputBorder

-0.74

GraphicsUnit

-0.72

gonic

-0.71

Portale

-0.71

 Winaray

-0.67

 Camara

-0.67

osene

-0.67

POSITIVE LOGITS

Bif

0.97

Coff

0.95

Haf

0.93

Sif

0.93

Bof

0.92

MCF

0.92

Cef

0.92

Bif

0.91

 Tuff

0.89

Mif

0.88

Activations Density 0.681%

specific medical abbreviations and related terms

No Comments

No Known Activations