INDEX

Explanations

references to Canadian entities

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

oldemort

-0.75

atz

-0.74

%]

-0.72

spell

-0.72

nyder

-0.72

chery

-0.70

finding

-0.69

wright

-0.69

uden

-0.69

JPM

-0.69

POSITIVE LOGITS

 Forces

1.04

 Tire

1.04

 Broadcasting

0.99

apolis

0.95

 Institutes

0.81

 Union

0.81

 Press

0.80

 Geographic

0.77

 Idol

0.77

 Nations

0.76

Activations Density 0.070%

references to Canadian entities

No Comments

No Known Activations