INDEX

Explanations

references to politicians or political figures

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "sens" in various contexts

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

 Zimbabwe

-0.67

 Maker

-0.67

 Springer

-0.66

 Gamb

-0.65

 Georgian

-0.62

maker

-0.60

 Proof

-0.59

 Carnegie

-0.59

 Shelter

-0.58

 Newton

-0.58

POSITIVE LOGITS

itivity

1.43

ibly

1.28

itives

1.26

itive

1.22

ibility

1.19

ibilities

1.15

orial

1.15

atile

1.14

itiveness

1.12

ual

1.12

Activations Density 0.053%

references to politicians or political figures

occurrences of the word "sens" in various contexts

No Comments

No Known Activations