INDEX

Explanations

words related to prioritization and organization

oai_token-act-pair · gpt-3.5-turbo

terms related to prioritization and ranking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

lv

-0.81

adal

-0.75

Newsletter

-0.75

iHUD

-0.73

Jenn

-0.73

found

-0.71

Assembly

-0.71

null

-0.68

FORMATION

-0.68

aghd

-0.68

POSITIVE LOGITS

 priorit

1.21

 prioritize

1.06

 priority

0.96

itism

0.91

priority

0.91

 priorities

0.90

efully

0.85

 allocation

0.82

 Priority

0.80

rals

0.77

Activations Density 0.013%

words related to prioritization and organization

terms related to prioritization and ranking

No Comments

No Known Activations