INDEX

Explanations

names and titles mentioning specific individuals or institutions, particularly focusing on surnames

oai_token-act-pair · gpt-3.5-turbo

words related to names or identities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 steep

-0.57

 reality

-0.56

 conservative

-0.56

 CODE

-0.55

 scra

-0.54

FUL

-0.54

 broadcasters

-0.54

 conservatives

-0.54

PLAY

-0.53

 compassionate

-0.53

POSITIVE LOGITS

1.78

1.58

icz

1.52

1.49

1.33

aan

1.26

oa

1.24

ski

1.23

xual

1.22

ti

1.22

Activations Density 0.298%

names and titles mentioning specific individuals or institutions, particularly focusing on surnames

words related to names or identities

No Comments

No Known Activations