INDEX

Explanations

information related to criminal investigations or suspicions

oai_token-act-pair · gpt-3.5-turbo

terms associated with criminal activity and investigations

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

often

-0.66

omics

-0.65

 explores

-0.64

iku

-0.63

ologies

-0.61

ggles

-0.61

 partName

-0.60

cour

-0.60

wrapper

-0.60

 strives

-0.59

POSITIVE LOGITS

 obstruction

0.75

 improper

0.71

 incrim

0.70

emort

0.69

 unlawful

0.69

 imminent

0.69

 Bulgar

0.69

 intruder

0.68

 undet

0.68

 exha

0.67

Activations Density 1.329%

information related to criminal investigations or suspicions

terms associated with criminal activity and investigations

No Comments

No Known Activations