INDEX

Explanations

phrases expressing varying degrees of expectation

oai_token-act-pair · gpt-3.5-turbo

phrases expressing expectations or anticipations

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

hops

-0.72

aunder

-0.68

ohyd

-0.66

ohydrate

-0.64

anski

-0.61

anco

-0.61

alde

-0.60

 Cheong

-0.60

umbered

-0.60

oche

-0.59

POSITIVE LOGITS

 payoff

0.82

 reaction

0.78

 audience

0.77

 wrath

0.74

 outcome

0.73

 backlash

0.71

 imminent

0.70

 reactions

0.69

0.67

SpaceEngineers

0.67

Activations Density 0.157%

phrases expressing varying degrees of expectation

phrases expressing expectations or anticipations

No Comments

No Known Activations