INDEX

Explanations

questions starting with "Why."

oai_token-act-pair · gpt-3.5-turbo

questions and phrases that express uncertainty or curiosity about reasons and explanations

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

 ILCS

-0.80

 icing

-0.67

OLOGY

-0.62

ibus

-0.61

 kilometres

-0.60

combe

-0.58

ylan

-0.58

achus

-0.57

\\\\\\\\\\\\\\\\

-0.57

atellite

-0.57

POSITIVE LOGITS

ãĢĳ

0.71

ppo

0.67

]).

0.66

 Matters

0.66

so

0.65

ãĤ»

0.65

ug

0.65

]),

0.64

 Hebdo

0.63

 differently

0.63

Activations Density 0.270%

questions starting with "Why."

questions and phrases that express uncertainty or curiosity about reasons and explanations

No Comments

No Known Activations