INDEX

Explanations

references to things related to the United States

oai_token-act-pair · gpt-3.5-turbo

mentions of the United States and related entities or officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

votes

-0.69

antry

-0.68

archy

-0.67

purpose

-0.61

 TAMADRA

-0.61

literally

-0.61

senal

-0.60

 SERVICE

-0.60

liv

-0.58

 Seym

-0.58

POSITIVE LOGITS

 embassy

0.99

 consulate

0.94

 Embassy

0.94

 consultancy

0.83

ileaks

0.81

 firm

0.76

 extradition

0.76

 Samoa

0.75

 diplomatic

0.74

 diplomat

0.74

Activations Density 0.381%

references to things related to the United States

mentions of the United States and related entities or officials

No Comments

No Known Activations