INDEX

Explanations

names of politicians and their corresponding official positions

oai_token-act-pair · gpt-3.5-turbo

terms related to government positions and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Denver

-0.89

 Toledo

-0.84

Miami

-0.83

 Filipino

-0.82

guyen

-0.82

 Guam

-0.81

 neighboring

-0.81

 Hawai

-0.81

 Navajo

-0.79

 Gree

-0.78

POSITIVE LOGITS

 Â£

1.12

Â£

1.06

 criticised

1.05

 Brexit

1.04

 Miliband

1.04

MPs

1.02

 apologised

1.01

Labour

1.01

Brexit

1.00

MP

1.00

Activations Density 0.217%

names of politicians and their corresponding official positions

terms related to government positions and roles

No Comments

No Known Activations