INDEX

Explanations

terms related to unintended secondary results or consequences

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "product."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ITED

-0.75

CLASSIFIED

-0.67

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.64

ARP

-0.63

 Shades

-0.62

 NOTICE

-0.62

 mosqu

-0.61

apo

-0.60

 Tarant

-0.60

[|

-0.60

POSITIVE LOGITS

ivity

1.18

ively

1.15

iveness

1.03

ivities

0.98

ions

0.87

arian

0.79

iation

0.79

Hunt

0.76

ivist

0.76

ogenous

0.75

Activations Density 0.019%

terms related to unintended secondary results or consequences

references to the concept of "product."

No Comments

No Known Activations