INDEX

Explanations

words related to debate or discussion

oai_token-act-pair · gpt-3.5-turbo

terms related to discussions or debates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

eared

-0.80

EMA

-0.74

nings

-0.74

eled

-0.74

alty

-0.72

of

-0.72

uras

-0.70

ages

-0.69

gencies

-0.68

ARS

-0.67

POSITIVE LOGITS

 debated

1.12

 debating

1.07

 debates

0.98

 debate

0.89

 unanimously

0.86

 Debate

0.85

nesday

0.73

wik

0.73

 undecided

0.73

halla

0.72

Activations Density 0.010%

words related to debate or discussion

terms related to discussions or debates

No Comments

No Known Activations