INDEX

Explanations

phrases related to decision-making

oai_token-act-pair · gpt-3.5-turbo

references to decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

anti

-0.78

Versions

-0.68

bing

-0.67

vae

-0.67

amen

-0.64

Legend

-0.63

icas

-0.62

Tur

-0.62

iday

-0.61

izont

-0.61

POSITIVE LOGITS

 decisions

1.06

 makers

0.91

 maker

0.86

 regarding

0.83

 choices

0.79

 whether

0.78

 concerning

0.77

 decision

0.77

 wisely

0.75

 involving

0.74

Activations Density 0.042%

phrases related to decision-making

references to decision-making processes

No Comments

No Known Activations