INDEX

Explanations

ambiguous questions about the meaning of something

oai_token-act-pair · gpt-3.5-turbo

phrases questioning the significance or implications of various topics

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

cler

-0.69

Mech

-0.68

hma

-0.67

ortex

-0.67

tk

-0.67

©¶æ

-0.66

mens

-0.65

attery

-0.65

ttes

-0.65

iti

-0.64

POSITIVE LOGITS

rawdownloadcloneembedreportprint

0.66

 culturally

0.65

 migrants

0.64

pling

0.63

Ð½

0.62

 exactly

0.62

Ð»

0.61

ELL

0.61

 depends

0.61

inav

0.60

Activations Density 0.011%

ambiguous questions about the meaning of something

phrases questioning the significance or implications of various topics

No Comments

No Known Activations