INDEX

Explanations

alternating words or phrases

oai_token-act-pair · gpt-3.5-turbo

words related to alternatives and opportunities

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

âķĲâķĲ

-0.68

birds

-0.68

flies

-0.67

foot

-0.66

 Divinity

-0.66

 relaxation

-0.65

bird

-0.64

nikov

-0.63

footed

-0.63

hower

-0.62

POSITIVE LOGITS

ately

1.33

ates

1.26

acy

1.26

acies

1.23

atell

1.19

atives

1.14

alis

1.01

itives

0.96

atus

0.96

ature

0.93

Activations Density 0.027%

alternating words or phrases

words related to alternatives and opportunities

No Comments

No Known Activations