INDEX

Explanations

words related to inclusion or being part of a group or list

oai_token-act-pair · gpt-3.5-turbo

references to inclusion or being part of a group or category

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mia

-0.70

aeus

-0.66

ffect

-0.66

ents

-0.65

 greed

-0.64

iger

-0.63

Eva

-0.63

ynchron

-0.62

 persistence

-0.61

ickey

-0.60

POSITIVE LOGITS

ynski

0.74

 Vaugh

0.72

 Schedule

0.72

 Appendix

0.70

estone

0.70

 "$:/

0.69

quished

0.66

 supplemental

0.66

 liner

0.65

 discussions

0.65

Activations Density 0.225%

words related to inclusion or being part of a group or list

references to inclusion or being part of a group or category

No Comments

No Known Activations