INDEX

Explanations

references to specific institutions or authorities

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

 <<<<<<<<<<<<<<

-0.67

 selve

-0.62

 disambiguazione

-0.60

TypedDataSet

-0.56

SBATCH

-0.55

rmtree

-0.52

hlungen

-0.52

msgTypes

-0.51

 actual

-0.51

 thérape

-0.50

POSITIVE LOGITS

 Jefus

0.70

Efq

0.68

recently

0.60

felves

0.59

 recently

0.59

intar

0.58

InstanceState

0.56

 別注

0.56

 recientemente

0.55

 недавно

0.54

Activations Density 0.404%

references to specific institutions or authorities

No Comments

No Known Activations