INDEX

Explanations

references to clerics and religious leaders, particularly in the context of Shia Islam

oai_token-act-pair · gpt-3.5-turbo

references to clerics and leaders in a religious or political context

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

 Packers

-0.81

 Hitch

-0.77

 Hawth

-0.76

 Rover

-0.76

 Yards

-0.75

 Pegasus

-0.74

 Detect

-0.73

 Galaxy

-0.73

 Oregon

-0.73

 Dock

-0.73

POSITIVE LOGITS

 clerics

0.95

istani

0.93

onite

0.89

 dictatorship

0.88

 cleric

0.87

 Hussein

0.85

astically

0.84

habi

0.83

doms

0.83

ollah

0.83

Activations Density 0.053%

references to clerics and religious leaders, particularly in the context of Shia Islam

references to clerics and leaders in a religious or political context

No Comments

No Known Activations