INDEX

Explanations

phrases related to actions or processes

oai_token-act-pair · gpt-3.5-turbo

references to interaction or connections between individuals or groups

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

inventoryQuantity

-0.89

ucci

-0.70

ãĤ´ãĥ³

-0.68

agate

-0.68

dated

-0.65

ãĤ¡

-0.64

iHUD

-0.63

agnar

-0.63

pox

-0.63

enthal

-0.62

POSITIVE LOGITS

 participants

1.47

 individuals

1.43

 citizens

1.29

 users

1.21

 members

1.21

 persons

1.19

 contestants

1.19

 adults

1.19

 humans

1.18

 people

1.18

Activations Density 0.899%

phrases related to actions or processes

references to interaction or connections between individuals or groups

No Comments

No Known Activations