INDEX

Explanations

names or terms related to individuals known for specific actions or roles

oai_token-act-pair · gpt-3.5-turbo

names of individuals and organizations involved in conflicts

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

Balt

-0.78

col

-0.77

âĸ¬

-0.73

 Siber

-0.72

Temp

-0.69

Prim

-0.67

Lear

-0.66

actionDate

-0.66

 horm

-0.66

VAL

-0.65

POSITIVE LOGITS

oulos

0.76

oglu

0.74

 disappeared

0.63

 deserves

0.62

 Tsarnaev

0.62

 embraced

0.62

 TAMADRA

0.62

 celebrated

0.61

enegger

0.60

 left

0.60

Activations Density 0.266%

names or terms related to individuals known for specific actions or roles

names of individuals and organizations involved in conflicts

No Comments

No Known Activations