INDEX

Explanations

abbreviations commonly representing places or organizations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "UP."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ici

-0.70

 Jordan

-0.65

ãĥ©

-0.64

 Stark

-0.62

 judgment

-0.62

icial

-0.61

 judgement

-0.61

 judgments

-0.60

 deserts

-0.60

Jud

-0.59

POSITIVE LOGITS

UP

4.31

UP

1.98

up

1.94

ups

1.77

Up

1.60

DOWN

1.50

UV

1.40

OUT

1.37

UC

1.34

FU

1.27

Activations Density 0.006%

abbreviations commonly representing places or organizations

occurrences of the abbreviation "UP."

No Comments

No Known Activations