INDEX

Explanations

questions, commands, and statements that express a sense of urgency or importance

oai_token-act-pair · gpt-3.5-turbo

interrogative and reflective phrases expressing questioning or uncertainty

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

iggins

-0.73

 Peak

-0.62

Newsletter

-0.61

Mand

-0.59

ammy

-0.59

risis

-0.58

Exit

-0.57

 Sunshine

-0.57

election

-0.57

emin

-0.56

POSITIVE LOGITS

cause

0.84

fortunately

0.79

JV

0.73

 congr

0.73

 goddamn

0.68

 ********************************

0.67

tis

0.64

cffff

0.64

 preferably

0.63

 ****

0.63

Activations Density 0.581%

questions, commands, and statements that express a sense of urgency or importance

interrogative and reflective phrases expressing questioning or uncertainty

No Comments

No Known Activations