INDEX

Explanations

people from specific locations and their related behaviors or characteristics

oai_token-act-pair · gpt-3.5-turbo

references to groups of people, particularly individuals from specific states or regions

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

Fly

-0.72

parts

-0.70

suit

-0.66

okin

-0.65

oots

-0.65

ods

-0.64

 srfAttach

-0.64

red

-0.64

ORY

-0.63

Redd

-0.63

POSITIVE LOGITS

who

0.91

0.85

 Anonymous

0.82

paces

0.81

 residing

0.80

ktop

0.79

 alike

0.78

abouts

0.77

pace

0.76

 living

0.76

Activations Density 0.079%

people from specific locations and their related behaviors or characteristics

references to groups of people, particularly individuals from specific states or regions

No Comments

No Known Activations