INDEX

Explanations

proper nouns related to a specific location or brand

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to places and people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.91

interstitial

-0.76

BUG

-0.70

NBA

-0.69

\",

-0.65

roxy

-0.64

wolves

-0.64

éĹĺ

-0.62

uggets

-0.62

 concussion

-0.61

POSITIVE LOGITS

 Kash

3.59

Tat

2.06

 Shan

1.30

Kyr

0.97

 Tiff

0.93

avin

0.92

 Poverty

0.92

Ai

0.91

Wor

0.86

 Nare

0.86

Activations Density 0.029%

proper nouns related to a specific location or brand

proper nouns related to places and people

No Comments

No Known Activations