INDEX

Explanations

Spanish words with accents

oai_token-act-pair · gpt-3.5-turbo

instances of the suffix "ón" in Spanish words

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

croft

-0.78

pread

-0.76

enhagen

-0.75

 Bengal

-0.70

nut

-0.69

 tradem

-0.69

bler

-0.69

bie

-0.69

jri

-0.69

birth

-0.67

POSITIVE LOGITS

Ã³n

1.00

ica

0.86

pour

0.81

ican

0.80

uala

0.79

ional

0.79

ÃŃn

0.78

 JosÃ©

0.78

 para

0.78

ÃŃ

0.76

Activations Density 0.025%

Spanish words with accents

instances of the suffix "ón" in Spanish words

No Comments

No Known Activations