INDEX

Explanations

political oppositional terms

oai_token-act-pair · gpt-3.5-turbo

expressions of opposition or resistance to policies or proposals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 emanc

-0.73

 metab

-0.69

 Loch

-0.69

 Sinai

-0.66

 Hebdo

-0.64

 tranquil

-0.61

 crossing

-0.60

 crime

-0.59

enegger

-0.58

 calves

-0.58

POSITIVE LOGITS

onent

1.92

ortun

1.88

onents

1.88

osite

1.85

osition

1.83

osing

1.66

osed

1.56

ression

1.52

ressive

1.41

oses

1.36

Activations Density 0.016%

political oppositional terms

expressions of opposition or resistance to policies or proposals

No Comments

No Known Activations