INDEX

Explanations

references to components or parts of objects or systems

oai_token-act-pair · gpt-3.5-turbo

references to "components" or parts of a system or item

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

kers

-0.83

stretched

-0.76

standing

-0.75

bies

-0.74

ker

-0.72

fm

-0.69

bows

-0.68

chie

-0.67

hur

-0.66

worthy

-0.66

POSITIVE LOGITS

 components

0.98

 parts

0.89

 component

0.88

 subsystem

0.84

 Components

0.82

 additive

0.81

onents

0.79

IAL

0.76

ancial

0.74

ially

0.73

Activations Density 0.016%

references to components or parts of objects or systems

references to "components" or parts of a system or item

No Comments

No Known Activations