INDEX

Explanations

cuisines from different countries

oai_token-act-pair · gpt-3.5-turbo

names of nationalities and cuisines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

etsk

-0.89

ividual

-0.88

ueller

-0.81

utonium

-0.79

alions

-0.78

odder

-0.76

ashington

-0.74

iscons

-0.74

vable

-0.74

ertodd

-0.74

POSITIVE LOGITS

 mystic

0.99

 cuisine

0.96

 monk

0.90

 lantern

0.83

esque

0.82

 delic

0.82

 peasant

0.81

 cooking

0.80

 themed

0.79

istani

0.78

Activations Density 0.123%

cuisines from different countries

names of nationalities and cuisines

No Comments

No Known Activations