INDEX

Explanations

references to military ranks and positions

oai_token-act-pair · gpt-3.5-turbo

references to military ranks and positions

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

izon

-0.76

esville

-0.74

âĶģ

-0.74

ãĥĥãĤ¯

-0.70

DAY

-0.69

dos

-0.68

ounding

-0.67

itiveness

-0.67

icultural

-0.66

oise

-0.65

POSITIVE LOGITS

utenant

0.95

 corps

0.82

ially

0.82

 stationed

0.76

 officer

0.72

 colonel

0.72

 officers

0.71

 overseeing

0.71

ials

0.70

geant

0.70

Activations Density 0.035%

references to military ranks and positions

references to military ranks and positions

No Comments

No Known Activations