INDEX

Explanations

sentences related to hypothetical scenarios or future possibilities

oai_token-act-pair · gpt-3.5-turbo

conditional phrases questioning future outcomes

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

lance

-0.67

enegger

-0.66

agonists

-0.63

visors

-0.63

quartered

-0.63

rers

-0.63

ivered

-0.62

ournals

-0.62

inel

-0.61

 ceased

-0.61

POSITIVE LOGITS

ãĤµ

0.71

?:

0.69

çĲ

0.65

?,

0.63

/$

0.62

 Syria

0.61

RTX

0.59

åŃ

0.59

piring

0.59

actly

0.58

Activations Density 0.272%

sentences related to hypothetical scenarios or future possibilities

conditional phrases questioning future outcomes

No Comments

No Known Activations