INDEX

Explanations

mentions of emissions and related terms

oai_token-act-pair · gpt-3.5-turbo

references to emissions, particularly regarding environmental policies and carbon output

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

uscript

-0.73

 Orth

-0.70

 Bread

-0.67

 Onion

-0.67

 Psychiatric

-0.66

orio

-0.66

IME

-0.66

amina

-0.66

ivas

-0.66

slice

-0.66

POSITIVE LOGITS

 emissions

1.33

 dioxide

1.13

 reductions

1.11

 emission

1.10

 emitted

1.07

 emitting

1.07

 gases

1.05

 pollution

1.03

 pollutants

1.00

 emit

0.97

Activations Density 0.065%

mentions of emissions and related terms

references to emissions, particularly regarding environmental policies and carbon output

No Comments

No Known Activations