INDEX

Explanations

mentions or phrases related to the term "Active"

oai_token-act-pair · gpt-3.5-turbo

references to "Active Directory" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

bill

-0.67

Miller

-0.67

flies

-0.63

anie

-0.60

pper

-0.60

 Mand

-0.60

 Yiannopoulos

-0.59

geon

-0.58

 transcripts

-0.57

½

-0.57

POSITIVE LOGITS

ives

1.09

ively

0.87

igue

0.85

Active

0.82

iveness

0.81

ived

0.80

iences

0.78

active

0.78

tymology

0.77

ivity

0.77

Activations Density 0.017%

mentions or phrases related to the term "Active"

references to "Active Directory" and related concepts

No Comments

No Known Activations