INDEX

Explanations

proper nouns of large cities

oai_token-act-pair · gpt-3.5-turbo

references to cities and urban environments

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

raviolet

-0.79

arial

-0.74

iasis

-0.71

iece

-0.70

tsy

-0.69

gotten

-0.67

selection

-0.67

yip

-0.66

aye

-0.66

SourceFile

-0.65

POSITIVE LOGITS

chool

0.92

scape

0.89

folk

0.87

 mayors

0.86

wide

0.81

hips

0.78

 landmarks

0.76

hare

0.75

 museums

0.72

 skyline

0.72

Activations Density 0.033%

proper nouns of large cities

references to cities and urban environments

No Comments

No Known Activations