INDEX

Explanations

statements or written communications issued by individuals

oai_token-act-pair · gpt-3.5-turbo

references to official communications, such as statements, reports, and letters

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Authors

-0.62

comes

-0.59

acists

-0.57

ances

-0.57

 encounters

-0.57

ayed

-0.56

icides

-0.55

glers

-0.54

 breeds

-0.54

 chants

-0.53

POSITIVE LOGITS

 titled

1.11

 stating

1.11

 outlining

1.09

 indicating

1.04

 saying

1.04

 detailing

1.03

 thanking

1.02

 alleging

1.01

 entitled

0.98

 apologizing

0.98

Activations Density 0.219%

statements or written communications issued by individuals

references to official communications, such as statements, reports, and letters

No Comments

No Known Activations