INDEX

Explanations

words related to various types of start or beginning, as well as chronological markers

oai_token-act-pair · gpt-3.5-turbo

words indicating the start or progression of events or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Ag

-0.67

bert

-0.67

weed

-0.65

ANA

-0.65

Matrix

-0.64

rehens

-0.61

ETF

-0.58

onz

-0.58

parency

-0.58

agg

-0.58

POSITIVE LOGITS

etheless

0.74

rul

0.70

IU

0.69

 theirs

0.67

 hers

0.62

 thirsty

0.61

 unprotected

0.61

KE

0.59

 substituted

0.58

 destro

0.58

Activations Density 1.085%

words related to various types of start or beginning, as well as chronological markers

words indicating the start or progression of events or concepts

No Comments

No Known Activations