INDEX

Explanations

questions and answers

oai_token-act-pair · gpt-3.5-turbo

phrases that present answers to questions or resolutions to queries

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

wana

-0.80

awar

-0.70

erker

-0.68

robat

-0.68

akin

-0.67

 DRAG

-0.67

::::::::

-0.66

arnaev

-0.65

ony

-0.63

 Vengeance

-0.62

POSITIVE LOGITS

ysis

1.12

answer

1.01

 answ

0.97

 answer

0.94

swers

0.88

 answered

0.86

 thereto

0.84

Answer

0.80

 answering

0.79

answered

0.76

Activations Density 0.022%

questions and answers

phrases that present answers to questions or resolutions to queries

No Comments

No Known Activations