INDEX

Explanations

phrases related to sequels or continuations of something

oai_token-act-pair · gpt-3.5-turbo

references to follow-up actions or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 DRAG

-0.69

 elim

-0.63

 elastic

-0.62

 ILCS

-0.62

Aut

-0.61

 helic

-0.61

 helicopters

-0.61

 nerv

-0.61

 benefic

-0.59

 facet

-0.58

POSITIVE LOGITS

up

1.46

through

1.31

ups

1.16

phrase

1.15

along

1.13

word

1.05

down

1.04

advertisement

1.04

release

1.01

tale

1.01

Activations Density 0.035%

phrases related to sequels or continuations of something

references to follow-up actions or reports

No Comments

No Known Activations