INDEX

Explanations

words related to transportation infrastructure, specifically focusing on train lines

oai_token-act-pair · gpt-3.5-turbo

terms related to public transportation lines and projects

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Folder

-0.79

luaj

-0.73

racuse

-0.73

rieved

-0.73

sonian

-0.71

ubuntu

-0.66

 heap

-0.65

alien

-0.65

Alien

-0.65

eanor

-0.65

POSITIVE LOGITS

 buses

1.16

 Transit

1.10

 trains

1.00

 Amtrak

0.95

 stations

0.92

Route

0.91

 routes

0.91

route

0.91

 Rail

0.89

roads

0.89

Activations Density 0.171%

words related to transportation infrastructure, specifically focusing on train lines

terms related to public transportation lines and projects

No Known Activations