INDEX

Explanations

mentions of former individuals or things

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "ex-" indicating former status or identity

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 GOODMAN

-0.86

 Sabha

-0.81

ãĤ¤ãĥĪ

-0.80

arity

-0.74

jriwal

-0.67

WAYS

-0.66

 Flavoring

-0.66

OUP

-0.65

hower

-0.64

GoldMagikarp

-0.64

POSITIVE LOGITS

clamation

1.25

ogenous

1.11

uber

1.09

orbit

1.08

clud

1.05

terior

1.03

uded

1.01

oplan

1.01

uding

0.99

communication

0.94

Activations Density 0.011%

mentions of former individuals or things

instances of the prefix "ex-" indicating former status or identity

No Comments

No Known Activations