INDEX

Explanations

phrases related to criminal activities, particularly murders

oai_token-act-pair · gpt-3.5-turbo

references to the concept of murder

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

wcsstore

-0.76

BuyableInstoreAndOnline

-0.75

Cola

-0.74

UTC

-0.72

 Enlight

-0.67

Dub

-0.67

iannopoulos

-0.66

XM

-0.65

uve

-0.65

 REPL

-0.64

POSITIVE LOGITS

 spree

1.14

 murder

0.99

ously

0.99

hyde

0.89

 rampage

0.88

 homicide

0.87

 murders

0.87

 mysteries

0.86

 victim

0.86

 murderer

0.84

Activations Density 0.035%

phrases related to criminal activities, particularly murders

references to the concept of murder

No Comments

No Known Activations