INDEX

Explanations

phrases related to political events and opinions

oai_token-act-pair · gpt-3.5-turbo

references to political events and figures

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

ulates

-0.67

etermin

-0.67

otin

-0.66

 climbs

-0.65

 ranges

-0.63

 advises

-0.63

 presses

-0.63

uces

-0.62

ati

-0.60

 muse

-0.60

POSITIVE LOGITS

didn

1.27

Had

1.22

 Didn

1.21

Was

1.14

 lacked

1.11

Had

1.10

Was

1.09

 didn

1.07

 hindsight

1.05

did

1.05

Activations Density 1.021%

phrases related to political events and opinions

references to political events and figures

No Comments

No Known Activations