INDEX

Explanations

terms related to specific areas of study or disciplines, such as neuroscience, astrophysics, or law enforcement

oai_token-act-pair · gpt-3.5-turbo

prefixes and roots related to scientific and technical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Legal

-0.74

Reloaded

-0.73

 SHARES

-0.72

 Principle

-0.71

 Financial

-0.71

 Reserve

-0.70

 Arrest

-0.70

 Worldwide

-0.69

 Economics

-0.69

 Loans

-0.69

POSITIVE LOGITS

ipers

0.94

onen

0.86

ippers

0.84

iper

0.84

usable

0.81

pos

0.81

amination

0.81

oling

0.79

ax

0.78

orc

0.77

Activations Density 0.180%

terms related to specific areas of study or disciplines, such as neuroscience, astrophysics, or law enforcement

prefixes and roots related to scientific and technical terminology

No Comments

No Known Activations