INDEX

Explanations

words containing the substring "ipped"

oai_token-act-pair · gpt-3.5-turbo

words related to being equipped or prepared

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 thereof

-0.76

 divers

-0.71

rhy

-0.68

 hist

-0.63

DA

-0.61

 fame

-0.60

 concrete

-0.60

de

-0.60

 quant

-0.59

 cast

-0.59

POSITIVE LOGITS

ipped

3.93

ipping

3.88

ips

2.27

ippers

1.88

IPP

1.88

ipper

1.75

ippy

1.71

IPS

1.68

ipp

1.61

ip

1.59

Activations Density 0.022%

words containing the substring "ipped"

words related to being equipped or prepared

No Comments

No Known Activations