INDEX

Explanations

locations and names of countries and individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographical locations, particularly Kuwait

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BOOK

-0.76

MENTS

-0.71

ringe

-0.67

backer

-0.64

ãģ¦

-0.64

MENT

-0.63

beit

-0.63

 energies

-0.63

yards

-0.61

berries

-0.60

POSITIVE LOGITS

amiya

0.84

igon

0.82

iya

0.80

waukee

0.80

ipedia

0.80

iyah

0.80

oi

0.80

iang

0.80

iak

0.79

iy

0.78

Activations Density 0.014%

locations and names of countries and individuals

mentions of specific geographical locations, particularly Kuwait

No Comments

No Known Activations