INDEX

Explanations

phrases related to violations or infringements of rules, laws, or rights

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of violating laws or rights

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

arger

-0.80

azor

-0.72

rike

-0.71

anka

-0.71

mad

-0.70

 Tycoon

-0.69

arij

-0.69

aws

-0.69

thora

-0.67

affer

-0.67

POSITIVE LOGITS

 unfocusedRange

0.89

 violations

0.88

 violation

0.80

viol

0.76

 violating

0.68

 Compliance

0.67

 compliance

0.67

 inhibition

0.66

 Viol

0.64

mson

0.64

Activations Density 0.038%

phrases related to violations or infringements of rules, laws, or rights

terms related to the concept of violating laws or rights

No Comments

No Known Activations