INDEX

Explanations

phrases indicating consequences or costs associated with certain actions

oai_token-act-pair · gpt-3.5-turbo

expressions indicating significant costs or consequences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

halla

-0.78

atis

-0.72

execute

-0.68

uploads

-0.68

docs

-0.63

USA

-0.62

eki

-0.59

hex

-0.58

 Fame

-0.58

produ

-0.57

POSITIVE LOGITS

 inconvenient

0.82

 expense

0.79

quickShipAvailable

0.79

 cost

0.73

 intersections

0.73

 heels

0.73

onement

0.72

 twilight

0.69

 costing

0.69

 risk

0.65

Activations Density 0.129%

phrases indicating consequences or costs associated with certain actions

expressions indicating significant costs or consequences

No Comments

No Known Activations