INDEX

Explanations

mentions of the word "Sin" followed by a number

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Sin" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

è¦ļéĨĴ

-1.02

enance

-0.75

dropping

-0.75

 downed

-0.74

 deficits

-0.73

ĵĺ

-0.72

psey

-0.70

¶ħ

-0.70

ITAL

-0.69

yright

-0.68

POSITIVE LOGITS

ners

1.09

atra

1.03

ned

1.00

estro

1.00

clair

0.98

uous

0.93

ister

0.92

ews

0.91

ja

0.86

oma

0.86

Activations Density 0.019%

mentions of the word "Sin" followed by a number

mentions of the word "Sin" in various contexts

No Comments

No Known Activations