INDEX

Explanations

proper nouns followed by location indicators

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or places related to individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 replay

-0.78

 Replay

-0.74

 indicators

-0.70

 headlights

-0.69

 benefic

-0.68

 criterion

-0.67

 thumbs

-0.66

 elim

-0.66

"%

-0.65

 revers

-0.65

POSITIVE LOGITS

based

1.57

area

1.48

centric

1.15

style

1.11

themed

1.10

sized

1.10

trained

1.08

focused

1.08

native

1.07

born

1.06

Activations Density 0.051%

proper nouns followed by location indicators

references to specific locations or places related to individuals and organizations

No Comments

No Known Activations