INDEX

Explanations

phrases related to decision-making and the impact of decisions

oai_token-act-pair · gpt-3.5-turbo

phrases related 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 hosts

-0.72

Versions

-0.70

trop

-0.66

 roofs

-0.65

 Reporting

-0.65

 depictions

-0.64

 Lamp

-0.64

 hosting

-0.62

pour

-0.62

 Offense

-0.62

POSITIVE LOGITS

 decisions

1.06

 unanimous

1.01

 irreversible

0.97

 regretted

0.96

 decision

0.96

 overr

0.95

 discretionary

0.94

 unilateral

0.93

 Decision

0.92

 unanimously

0.90

Activations Density 0.186%

phrases related to decision-making and the impact of decisions

phrases related to decision-making processes

No Comments

No Known Activations