INDEX

Explanations

references to reports or studies

oai_token-act-pair · gpt-3.5-turbo

specific references to official reports and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

agogue

-0.88

æ©

-0.81

twitch

-0.75

 masc

-0.72

Fans

-0.70

 vending

-0.69

pot

-0.68

lane

-0.68

locks

-0.67

 Craigslist

-0.67

POSITIVE LOGITS

 report

1.60

 Report

1.44

 findings

1.38

Report

1.32

 damning

1.32

report

1.25

 scathing

1.25

 audit

1.23

 conclusions

1.23

 recommendations

1.21

Activations Density 0.496%

references to reports or studies

specific references to official reports and statistics

No Comments

No Known Activations