INDEX

Explanations

words related to locations or addresses

oai_token-act-pair · gpt-3.5-turbo

references to locations or specific identifiers associated with places

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

child

-0.87

deen

-0.74

manship

-0.74

thing

-0.73

PDATE

-0.69

-0.68

isSpecialOrderable

-0.67

 Duchess

-0.67

boarding

-0.67

 Sacrifice

-0.67

POSITIVE LOGITS

atell

1.11

ator

0.97

ocity

0.97

entric

0.95

abulary

0.95

alf

0.95

ution

0.94

ombo

0.92

ality

0.89

uti

0.87

Activations Density 0.020%

words related to locations or addresses

references to locations or specific identifiers associated with places

No Comments

No Known Activations