INDEX

Explanations

words related to disputes, confrontation, and conflict

oai_token-act-pair · gpt-3.5-turbo

words related to actions or behaviors that disrupt or hinder

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DragonMagazine

-1.05

 objective

-0.77

Reviewer

-0.75

hyde

-0.73

channelAvailability

-0.69

 directive

-0.68

 identification

-0.67

 role

-0.67

 Millennium

-0.66

 occupation

-0.65

POSITIVE LOGITS

uously

1.08

oused

1.04

icating

1.01

iously

1.00

ously

0.96

inged

0.95

acing

0.95

ibly

0.93

isively

0.92

arily

0.92

Activations Density 0.332%

words related to disputes, confrontation, and conflict

words related to actions or behaviors that disrupt or hinder

No Comments

No Known Activations