INDEX

Explanations

instances of the word "they" followed by various actions or characteristics of the individuals referred to

oai_token-act-pair · gpt-3.5-turbo

information related to underestimation or failure in achieving goals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

emale

-0.81

itaire

-0.68

 Seym

-0.65

icter

-0.61

 Vaugh

-0.61

 destro

-0.57

 Moroc

-0.57

 referen

-0.55

 thous

-0.55

nesday

-0.54

POSITIVE LOGITS

 largeDownload

0.61

 JUSTICE

0.51

zbollah

0.49

 Shin

0.49

 unders

0.49

mos

0.48

 Guardians

0.48

 hurt

0.47

\":

0.46

CVE

0.46

Activations Density 1.311%

instances of the word "they" followed by various actions or characteristics of the individuals referred to

information related to underestimation or failure in achieving goals

No Comments

No Known Activations