INDEX

Explanations

reasons and justifications

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate multiple reasons or justifications

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

bilt

-0.71

ream

-0.71

xon

-0.69

esc

-0.67

 Pixie

-0.66

externalActionCode

-0.66

ibaba

-0.66

 franc

-0.65

quet

-0.64

 Nanto

-0.63

POSITIVE LOGITS

why

0.99

 reasons

0.94

pointers

0.90

 justifying

0.82

WHY

0.82

why

0.81

æĦ

0.81

 Reasons

0.81

 arguments

0.81

 explanations

0.78

Activations Density 0.023%

reasons and justifications

phrases that indicate multiple reasons or justifications

No Comments

No Known Activations