INDEX

Explanations

terms related to news headlines and articles

oai_token-act-pair · gpt-3.5-turbo

occurrences of numbers and their context in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 trump

-0.77

 license

-0.74

 tram

-0.73

 dece

-0.73

 veter

-0.71

 swall

-0.71

©¶æ

-0.69

 disciplines

-0.69

 dolphin

-0.69

 lifes

-0.68

POSITIVE LOGITS

Speaking

1.33

Meanwhile

1.28

According

1.24

Since

1.24

Using

1.23

Then

1.23

However

1.23

While

1.21

But

1.20

Similar

1.20

Activations Density 0.206%

terms related to news headlines and articles

occurrences of numbers and their context in the text

No Comments

No Known Activations