INDEX

Explanations

phrases related to specific events or actions

oai_token-act-pair · gpt-3.5-turbo

events and activities that have significance or impact

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

metics

-0.85

lip

-0.75

lev

-0.70

vin

-0.68

aws

-0.66

olen

-0.66

bestos

-0.64

obb

-0.64

adata

-0.64

krit

-0.62

POSITIVE LOGITS

 initiation

0.88

eers

0.84

 lasted

0.84

 lasts

0.81

goers

0.80

 commenced

0.76

 procession

0.75

 involving

0.75

 involves

0.74

eering

0.73

Activations Density 0.527%

phrases related to specific events or actions

events and activities that have significance or impact

No Comments

No Known Activations