INDEX

Explanations

locations or geographical features

oai_token-act-pair · gpt-3.5-turbo

elements related to specific locations or settings

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

 Scal

-0.55

ippi

-0.55

 Founders

-0.55

 Dele

-0.55

govtrack

-0.54

 privatization

-0.53

Klu

-0.52

 Gillespie

-0.51

Specifically

-0.51

 Wass

-0.50

POSITIVE LOGITS

 guiActiveUn

0.67

ileged

0.55

natureconservancy

0.53

xual

0.53

chan

0.52

 photographer

0.52

ãĤ¸

0.51

çĶ°

0.50

escape

0.50

ifice

0.49

Activations Density 1.784%

locations or geographical features

elements related to specific locations or settings

No Comments

No Known Activations