INDEX

Explanations

phrases related to lists

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the existence and attributes of extensive lists

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

 Samar

-0.74

BAT

-0.70

inea

-0.69

steen

-0.67

coni

-0.65

ãĥ¡

-0.64

 brakes

-0.62

Cath

-0.62

imity

-0.62

asaki

-0.61

POSITIVE LOGITS

 lists

0.87

 Lists

0.86

 sorted

0.84

 shelves

0.82

 curated

0.77

 alphabet

0.76

 excludes

0.75

 list

0.73

 listing

0.72

lists

0.70

Activations Density 0.454%

phrases related to lists

phrases indicating the existence and attributes of extensive lists

No Comments

No Known Activations