INDEX

Explanations

instances of the word "Chiefs" in sentences

oai_token-act-pair · gpt-3.5-turbo

references to the Chiefs, likely in a sports 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

mble

-1.08

nces

-0.87

enza

-0.85

ently

-0.84

encers

-0.77

angible

-0.77

PDATE

-0.74

ded

-0.72

furt

-0.72

ãĤ£

-0.72

POSITIVE LOGITS

 Chiefs

1.20

 Commissioners

0.74

mail

0.70

doms

0.70

 Lumpur

0.69

kat

0.69

 chiefs

0.68

 Council

0.65

 Royals

0.64

Chief

0.63

Activations Density 0.019%

instances of the word "Chiefs" in sentences

references to the Chiefs, likely in a sports context

No Comments

No Known Activations