INDEX

Explanations

symbols or characters used in a specific language or writing system

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

terday

-0.81

 decomp

-0.73

aimon

-0.64

TTL

-0.64

 dispers

-0.62

voy

-0.62

PTS

-0.62

 Bengal

-0.62

 Medline

-0.61

 mosaic

-0.59

POSITIVE LOGITS

ĸ

1.48

Ĩ

1.45

¹

1.42

ĺ

1.40

Ħ

1.36

Ķ

1.36

ı

1.32

·

1.32

Ī

1.32

ľ

1.31

Activations Density 0.009%

symbols or characters used in a specific language or writing system

special characters or symbols in the text

No Comments

No Known Activations