INDEX

Explanations

mentions of software demonstrations or exhibitions

oai_token-act-pair · gpt-3.5-turbo

references to software demonstrations or demo versions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

turn

-0.73

leans

-0.67

 punishment

-0.65

 Mysteries

-0.64

ricanes

-0.64

adia

-0.63

olia

-0.63

sea

-0.63

capacity

-0.62

laus

-0.62

POSITIVE LOGITS

eer

0.91

psey

0.85

 reel

0.84

stration

0.81

 taped

0.79

urated

0.79

 demo

0.78

 tapes

0.77

 demos

0.75

LAB

0.73

Activations Density 0.020%

mentions of software demonstrations or exhibitions

references to software demonstrations or demo versions

No Comments

No Known Activations