INDEX

Explanations

proper nouns, particularly names of people and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

ParallelGroup

-0.72

 Covid

-0.70

principalColumn

-0.70

NFT

-0.68

covid

-0.67

AxisAlignment

-0.67

 covid

-0.67

gatan

-0.66

 snippetHide

-0.66

 COVID

-0.65

POSITIVE LOGITS

 Obama

0.87

 iPod

0.86

Obama

0.85

 Sarkozy

0.85

 xrange

0.82

myspace

0.77

0.76

quiao

0.75

 Kinect

0.73

 Barack

0.70

Activations Density 1.237%

proper nouns, particularly names of people and locations

No Comments

No Known Activations