INDEX

Explanations

numbers that seem to have a special significance or pattern

oai_token-act-pair · gpt-3.5-turbo

specific numerical codes and identifiers related to organized data or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

EStreamFrame

-0.73

 classified

-0.71

 elig

-0.66

 ping

-0.65

Jiu

-0.64

 Americ

-0.63

cl

-0.63

kg

-0.63

EP

-0.63

ET

-0.61

POSITIVE LOGITS

1.29

1.22

1.21

1.20

1.19

Activations Density 0.058%

numbers that seem to have a special significance or pattern

specific numerical codes and identifiers related to organized data or classifications

No Comments

No Known Activations