INDEX

Explanations

French accented characters

oai_token-act-pair · gpt-3.5-turbo

instances of the character "é" in various contexts

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

utterstock

-0.80

pread

-0.75

INESS

-0.73

enged

-0.70

etsk

-0.68

 Cobra

-0.68

ageddon

-0.67

Spread

-0.65

 redistributed

-0.64

 Blazers

-0.64

POSITIVE LOGITS

lÃ©

1.19

rez

0.92

vez

0.92

 Dame

0.91

 Ã©

0.87

rÃ©

0.83

itÃ©

0.82

ration

0.82

cÃ©

0.82

Ã©

0.81

Activations Density 0.013%

French accented characters

instances of the character "é" in various contexts

No Comments

No Known Activations