INDEX

Explanations

references to services being provided or offered

oai_token-act-pair · gpt-3.5-turbo

terms related to various types of services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ross

-0.82

Ze

-0.71

isha

-0.71

lihood

-0.69

lein

-0.68

ged

-0.68

ivil

-0.67

ril

-0.65

ipolar

-0.64

ging

-0.63

POSITIVE LOGITS

 providers

1.37

 provider

1.36

 Provider

1.22

 rendered

1.16

 Provided

1.05

 furnished

0.84

 provided

0.83

Provider

0.81

 offered

0.79

 PROV

0.77

Activations Density 0.057%

references to services being provided or offered

terms related to various types of services

No Comments

No Known Activations