INDEX

Explanations

proper nouns and locations

oai_token-act-pair · gpt-3.5-turbo

references to a specific city or location

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

thood

-0.87

-0.84

ccoli

-0.84

Î³

-0.81

IQ

-0.80

istries

-0.75

ophen

-0.74

olitics

-0.73

ãĥīãĥ©

-0.73

witch

-0.72

POSITIVE LOGITS

 tallest

1.42

 adjoining

1.21

 roof

1.20

 roofs

1.18

 entire

1.17

 walls

1.15

 largest

1.15

 interior

1.12

 exterior

1.10

 oldest

1.10

Activations Density 0.504%

proper nouns and locations

references to a specific city or location

No Comments

No Known Activations