INDEX

Explanations

proper nouns related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

specific place names or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

evil

-0.76

authent

-0.74

-0.69

credit

-0.69

multipl

-0.69

indu

-0.69

EF

-0.69

Intel

-0.68

annis

-0.68

jin

-0.67

POSITIVE LOGITS

 Palace

1.07

 Stadium

0.95

 chamber

0.94

 avenue

0.91

 Station

0.90

 palace

0.88

 dome

0.88

 Coliseum

0.87

 Tower

0.87

 Blvd

0.86

Activations Density 0.452%

proper nouns related to geographical locations

specific place names or locations

No Comments

No Known Activations