INDEX

Explanations

technical or scientific terms related to research and health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 GenerationType

-0.63

QUADS

-0.62

zések

-0.59

 елның

-0.57

netinet

-0.57

cách

-0.56

ztus

-0.56

kezés

-0.56

PRNewswire

-0.55

localScale

-0.55

POSITIVE LOGITS

httphttps

0.74

 Italijanski

0.69

unmodifiable

0.67

(!__

0.61

 ClassNotFound

0.61

ieteur

0.58

 propOrder

0.56

showConfirm

0.56

TypedDataSet

0.56

joba

0.55

Activations Density 1.883%

technical or scientific terms related to research and health

No Comments

No Known Activations