INDEX

Explanations

markers or indicators in text

oai_token-act-pair · gpt-3.5-turbo

terms related to markers and indicators

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

Vaj

-0.73

 Proc

-0.69

 Hosp

-0.68

 Unic

-0.68

Cha

-0.67

bowl

-0.67

 Unified

-0.66

Commerce

-0.66

unb

-0.63

ceans

-0.63

POSITIVE LOGITS

 marker

3.95

 markers

3.52

 biomark

1.41

 marking

1.34

 mark

1.29

 markings

1.26

mark

1.24

 indicator

1.24

 plaque

1.19

 unmarked

1.16

Activations Density 0.012%

markers or indicators in text

terms related to markers and indicators

No Comments

No Known Activations