INDEX

Explanations

acronyms and specific terms related to various entities or systems

oai_token-act-pair · gpt-3.5-turbo

abbreviations or acronyms related to organizations, systems, or standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

iary

-0.89

istically

-0.85

tery

-0.84

ifications

-0.78

itates

-0.77

icity

-0.77

wagen

-0.76

omorphic

-0.75

istical

-0.75

selling

-0.74

POSITIVE LOGITS

VO

1.33

VEL

1.33

VER

1.32

LL

1.31

VICE

1.29

VEN

1.29

VIS

1.27

VOL

1.26

VE

1.24

ET

1.20

Activations Density 0.059%

acronyms and specific terms related to various entities or systems

abbreviations or acronyms related to organizations, systems, or standards

No Comments

No Known Activations