INDEX

Explanations

words related to technology or product names with 'X' as a dominant feature

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "X"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bett

-0.67

assetsadobe

-0.67

iott

-0.65

 Franch

-0.65

 rhet

-0.63

erest

-0.63

ustain

-0.63

 challeng

-0.62

Govern

-0.62

Ber

-0.62

POSITIVE LOGITS

3.45

2.32

1.89

XX

1.71

XV

1.69

XI

1.59

XM

1.56

XXX

1.56

XY

1.55

IX

1.54

Activations Density 0.023%

words related to technology or product names with 'X' as a dominant feature

occurrences of the letter "X"

No Comments

No Known Activations