INDEX

Explanations

declarations or promises of things that will not happen

oai_token-act-pair · gpt-3.5-turbo

negations or expressions of refusal

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

wrapper

-0.69

 Handbook

-0.67

 Measures

-0.66

Intern

-0.65

 Seasons

-0.65

Nice

-0.64

Maker

-0.63

quickShipAvailable

-0.63

 Strategy

-0.62

Nine

-0.62

POSITIVE LOGITS

 necessarily

1.24

icably

1.20

 tolerate

1.04

icable

1.03

 bother

1.00

bud

0.99

 hesitate

0.97

 suffice

0.89

be

0.88

 interfere

0.87

Activations Density 0.088%

declarations or promises of things that will not happen

negations or expressions of refusal

No Comments

No Known Activations