INDEX

Explanations

phrases related to complex or advanced concepts

oai_token-act-pair · gpt-3.5-turbo

phrases related to causes or consequences of events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hey

-0.58

NetMessage

-0.53

 Disapp

-0.52

 Nope

-0.52

iatus

-0.51

Leave

-0.50

[+

-0.50

 Corona

-0.50

 payday

-0.50

 Heard

-0.49

POSITIVE LOGITS

 therefore

1.36

 however

1.12

 moreover

1.01

 accordingly

0.92

 thus

0.86

 furthermore

0.85

 meanwhile

0.80

 consequently

0.79

 analogous

0.78

 likewise

0.78

Activations Density 1.281%

phrases related to complex or advanced concepts

phrases related to causes or consequences of events

No Comments

No Known Activations