INDEX

Explanations

mentions of urban-related terms or entities

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Urban"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

nesota

-0.82

utes

-0.72

utations

-0.71

tub

-0.70

hered

-0.70

ivity

-0.69

kens

-0.69

onement

-0.65

arers

-0.65

oned

-0.65

POSITIVE LOGITS

Ñĭ

0.90

owitz

0.74

oscope

0.73

 Dictionary

0.73

³

0.71

 Moving

0.71

ulus

0.69

atio

0.68

Ð°

0.68

ipal

0.67

Activations Density 0.031%

mentions of urban-related terms or entities

mentions of the word "Urban"

No Comments

No Known Activations