INDEX

Explanations

names of people or characters within a given context

oai_token-act-pair · gpt-3.5-turbo

words related to names and personal identifiers

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 DPRK

-0.66

 stockpile

-0.65

 daylight

-0.65

SPONSORED

-0.64

 ______

-0.63

 welfare

-0.63

 CTRL

-0.59

 scarcity

-0.59

 token

-0.58

 chronically

-0.58

POSITIVE LOGITS

akis

1.51

iere

1.45

otti

1.44

idis

1.43

neau

1.43

ini

1.43

opoulos

1.42

atos

1.42

ova

1.41

oux

1.39

Activations Density 0.285%

names of people or characters within a given context

words related to names and personal identifiers

No Known Activations