INDEX

Explanations

key phrases or terms related to text formatting, coding, or programming

oai_token-act-pair · gpt-3.5-turbo

punctuation and formatting elements within text

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

Ò

-0.70

istani

-0.70

Ã±o

-0.61

efe

-0.57

furt

-0.56

abwe

-0.56

artney

-0.56

æ©

-0.55

baugh

-0.55

ufact

-0.55

POSITIVE LOGITS

 Gleaming

0.59

 Tactics

0.56

 Meditation

0.55

MMO

0.54

 Dungeons

0.53

 EDITION

0.51

 Casual

0.51

 Conspiracy

0.50

 Misc

0.49

 EVENTS

0.49

Activations Density 1.086%

key phrases or terms related to text formatting, coding, or programming

punctuation and formatting elements within text

No Comments

No Known Activations