INDEX

Explanations

words related to a specific proper name - "Gore"

oai_token-act-pair · gpt-3.5-turbo

references to Al Gore and discussions about his actions or roles

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

istically

-1.23

istic

-1.09

istical

-1.00

adelphia

-0.94

istics

-0.87

iary

-0.77

ifying

-0.76

ifications

-0.72

icating

-0.72

icles

-0.71

POSITIVE LOGITS

milo

0.80

bare

0.80

ption

0.77

ĸļ

0.73

terness

0.71

hari

0.70

vernment

0.68

GN

0.68

ensibly

0.67

ean

0.67

Activations Density 0.141%

words related to a specific proper name - "Gore"

references to Al Gore and discussions about his actions or roles

No Comments

No Known Activations