INDEX

Explanations

words 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Teg

-0.68

 Crest

-0.67

Joy

-0.66

 Semi

-0.66

bun

-0.63

 densely

-0.63

 Territories

-0.62

Mub

-0.62

 Flag

-0.62

EL

-0.61

POSITIVE LOGITS

anchester

1.07

making

1.05

emort

1.03

awaru

1.01

redients

1.00

VIDIA

0.92

uration

0.91

roid

0.90

furt

0.90

ratulations

0.89

Activations Density 0.015%

words related to decision-making

references to decision-making processes

No Comments

No Known Activations