INDEX

Explanations

proper nouns related to companies or organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of organizations or companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Machines

-0.79

 Demons

-0.72

 Blades

-0.71

 perpetrators

-0.63

bats

-0.63

latest

-0.63

othy

-0.62

 Tanks

-0.62

 positives

-0.61

 Chambers

-0.61

POSITIVE LOGITS

 specializing

0.90

 whose

0.81

 named

0.80

 staffed

0.80

paio

0.79

 called

0.76

 Called

0.75

 classmate

0.74

mate

0.74

 subsidiary

0.71

Activations Density 0.269%

proper nouns related to companies or organizations

mentions of organizations or companies

No Comments

No Known Activations