INDEX

Explanations

verbs related to likelihood or probability

oai_token-act-pair · gpt-3.5-turbo

phrases indicating probability or likelihood

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

Cooldown

-0.74

yrights

-0.73

ellation

-0.72

quickShipAvailable

-0.71

RAW

-0.71

 Provided

-0.71

eport

-0.70

hai

-0.69

aepernick

-0.68

APTER

-0.68

POSITIVE LOGITS

 absorb

1.04

 engage

1.02

 spend

0.99

 confront

0.99

be

0.98

 participate

0.97

 reject

0.94

 enter

0.94

 earn

0.93

 interact

0.92

Activations Density 0.104%

verbs related to likelihood or probability

phrases indicating probability or likelihood

No Comments

No Known Activations