INDEX

Explanations

alphabetic characters followed by numbers or special characters

oai_token-act-pair · gpt-3.5-turbo

specific technical terms and identifiers related to coding and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 conflicted

-0.82

 polic

-0.74

 accrued

-0.73

 favor

-0.73

 seiz

-0.73

cod

-0.73

 kale

-0.72

 cher

-0.72

lim

-0.72

 compet

-0.71

POSITIVE LOGITS

Proof

1.28

World

1.24

Bl

1.24

Fl

1.22

Non

1.19

Fil

1.18

Active

1.18

Shut

1.18

En

1.17

Front

1.17

Activations Density 0.247%

alphabetic characters followed by numbers or special characters

specific technical terms and identifiers related to coding and programming

No Comments

No Known Activations