INDEX

Explanations

terms related to the word "tar"

oai_token-act-pair · gpt-3.5-turbo

references to tar

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

assetsadobe

-0.83

nesota

-0.82

hetti

-0.79

ĨĴ

-0.79

 Startup

-0.79

etts

-0.78

sense

-0.76

ļéĨĴ

-0.73

ItemTracker

-0.73

Interstitial

-0.72

POSITIVE LOGITS

 sands

1.22

tar

1.14

pee

0.82

 blister

0.79

balls

0.78

iffs

0.77

 puff

0.76

 blob

0.76

anium

0.75

 smear

0.75

Activations Density 0.008%

terms related to the word "tar"

references to tar

No Comments

No Known Activations