INDEX

Explanations

descriptive phrases conveying positive emotion

oai_token-act-pair · gpt-3.5-turbo

expressions of admiration or critique related to music, culture, and societal issues

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

CHAT

-0.72

ctors

-0.70

 Quit

-0.70

CAST

-0.66

veland

-0.66

 Courier

-0.65

cius

-0.64

eworthy

-0.64

 repro

-0.63

study

-0.63

POSITIVE LOGITS

 pesky

0.69

 Horizon

0.69

 morphed

0.67

ãĤ©

0.64

 Upton

0.63

isphere

0.62

 Ronaldo

0.61

é¾įå¥ĳå£«

0.60

footed

0.60

 Scream

0.59

Activations Density 0.367%

descriptive phrases conveying positive emotion

expressions of admiration or critique related to music, culture, and societal issues

No Comments

No Known Activations