INDEX

Explanations

years mentioned within parentheses

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and their contexts in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enta

-0.68

agog

-0.62

aban

-0.62

zers

-0.62

arna

-0.60

tube

-0.60

 therap

-0.60

kus

-0.59

elling

-0.59

liga

-0.59

POSITIVE LOGITS

0.69

then

0.67

etc

0.63

 then

0.62

 whereas

0.62

 nevertheless

0.61

google

0.60

selves

0.60

 secondly

0.60

 furthermore

0.59

Activations Density 0.150%

years mentioned within parentheses

punctuation marks and their contexts in a text

No Comments

No Known Activations