INDEX

Explanations

mentions of and related to law enforcement personnel, specifically sheriffs

oai_token-act-pair · gpt-3.5-turbo

references to law enforcement officials, specifically sheriffs

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

-0.82

lihood

-0.81

jad

-0.78

 Centauri

-0.74

ted

-0.73

ankind

-0.67

ced

-0.66

VEN

-0.66

ptions

-0.66

pace

-0.64

POSITIVE LOGITS

 sheriff

1.04

 Sheriff

1.01

osate

0.90

 commissioner

0.87

 coroner

0.82

 deputies

0.80

icio

0.79

Sher

0.76

 commissioners

0.76

 Arpaio

0.76

Activations Density 0.015%

mentions of and related to law enforcement personnel, specifically sheriffs

references to law enforcement officials, specifically sheriffs

No Comments

No Known Activations