INDEX

Explanations

phrases related to specific product or brand names

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the existence or definition of a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Footnote

-0.70

*/

-0.68

âĨĳ

-0.67

INTON

-0.65

ogeneity

-0.63

eter

-0.62

Others

-0.62

anger

-0.61

 traged

-0.61

Versions

-0.61

POSITIVE LOGITS

rael

1.10

 pleased

0.99

 rated

0.96

 hereby

0.92

 proud

0.90

senal

0.90

ometric

0.82

 thrilled

0.81

 saddened

0.76

 slated

0.75

Activations Density 0.157%

phrases related to specific product or brand names

phrases indicating the existence or definition of a subject

No Comments

No Known Activations