INDEX

Explanations

terms related to reports, interviews, and documentation

oai_token-act-pair · gpt-3.5-turbo

connections between various reports and accounts in news articles

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

ãĤ¼ãĤ¦ãĤ¹

-0.87

itans

-0.79

aires

-0.78

 disadvantaged

-0.77

hei

-0.70

 dwarves

-0.70

anooga

-0.68

advant

-0.68

Ã³

-0.67

ampires

-0.67

POSITIVE LOGITS

 interviews

1.05

 subsequent

1.01

 statements

0.98

 unpublished

0.96

 transcripts

0.95

 accompanying

0.94

 screenshots

0.94

 excerpts

0.92

 filings

0.91

 Statements

0.88

Activations Density 0.458%

terms related to reports, interviews, and documentation

connections between various reports and accounts in news articles

No Comments

No Known Activations