INDEX

Explanations

terms that contain the substring "ined"

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of "dining" or eating experiences

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

AGES

-0.81

WM

-0.69

channelAvailability

-0.69

aptic

-0.68

Wim

-0.68

 Asheville

-0.65

BP

-0.64

 Debor

-0.64

ilities

-0.64

fair

-0.62

POSITIVE LOGITS

ined

0.98

ining

0.96

 enrichment

0.75

igm

0.74

iners

0.70

jad

0.70

 sights

0.69

 tong

0.69

creen

0.67

inery

0.65

Activations Density 0.018%

terms that contain the substring "ined"

words related to the concept of "dining" or eating experiences

No Comments

No Known Activations