INDEX

Explanations

proper nouns or names with a specific pattern consisting of characters with unusual symbols interleaved within

oai_token-act-pair · gpt-3.5-turbo

references to academic institutions or locations

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

essa

-0.78

-0.77

 Sally

-0.74

-0.72

-0.69

-0.68

-0.66

ont

-0.65

 Reincarn

-0.65

POSITIVE LOGITS

1.23

1.22

bs

1.20

bg

1.19

Bs

1.18

BB

1.18

bm

1.18

BA

1.16

BD

1.15

BR

1.15

Activations Density 0.587%

proper nouns or names with a specific pattern consisting of characters with unusual symbols interleaved within

references to academic institutions or locations

No Comments

No Known Activations