INDEX

Explanations

events or activities that are starting or beginning

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the initiation of an event or activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

é¾įå

-0.87

WARE

-0.79

sonian

-0.67

enne

-0.65

forts

-0.64

worn

-0.63

okin

-0.63

fed

-0.63

ãĥĸ

-0.62

mong

-0.62

POSITIVE LOGITS

uberty

0.70

ratulations

0.69

 Archdemon

0.69

odcast

0.67

Interstitial

0.66

 takeoff

0.65

thood

0.65

 Doors

0.63

reon

0.62

 âĸº

0.62

Activations Density 0.033%

events or activities that are starting or beginning

phrases that indicate the initiation of an event or activity

No Comments

No Known Activations