INDEX

Explanations

technical terms related to software development and computer systems

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

terms indicating significance or importance, often in the context of features or updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

ults

-0.84

ULTS

-0.81

ravel

-0.75

rils

-0.72

elf

-0.72

etimes

-0.69

iless

-0.68

ograms

-0.67

olson

-0.67

events

-0.66

POSITIVE LOGITS

 drawback

1.53

 disadvantage

1.39

 downside

1.34

 limitation

1.30

 advantage

1.26

 pecul

1.14

 annoyance

1.13

 weakness

1.11

 benefit

1.10

 downfall

1.10

Activations Density 0.333%

technical terms related to software development and computer systems

terms indicating significance or importance, often in the context of features or updates

No Comments

No Known Activations