INDEX

Explanations

locations or settings

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate locations or contexts within societal issues

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Cheong

-0.76

azines

-0.71

engers

-0.69

bats

-0.67

 Clayton

-0.66

atars

-0.64

 Denis

-0.63

 Drivers

-0.63

 Bott

-0.62

insk

-0.59

POSITIVE LOGITS

luaj

0.92

¿½

0.81

 thri

0.79

¥µ

0.78

 dominated

0.78

 starved

0.75

 neither

0.71

 barely

0.70

 wors

0.70

 staffed

0.70

Activations Density 0.276%

locations or settings

phrases that indicate locations or contexts within societal issues

No Comments

No Known Activations