INDEX

Explanations

references to the name "Rod" at different contexts or in different forms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "rod."

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

 affordable

-0.63

 reservations

-0.62

 congreg

-0.61

 Advent

-0.60

 Mission

-0.60

 enrollment

-0.59

 Editors

-0.58

 requested

-0.58

 reservation

-0.57

 floats

-0.56

POSITIVE LOGITS

rod

4.85

ro

1.43

Rod

1.33

roth

1.21

rog

1.20

rology

1.19

rol

1.19

rod

1.18

ros

1.18

rad

1.16

Activations Density 0.012%

references to the name "Rod" at different contexts or in different forms

occurrences of the word "rod."

No Comments

No Known Activations