INDEX

Explanations

prefixes related to placement or sequence

oai_token-act-pair · gpt-3.5-turbo

phrases related to preemptive actions or measures

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

 Schmidt

-0.73

 Stranger

-0.71

DeV

-0.69

Nig

-0.68

 Holding

-0.67

 merits

-0.67

 DRAG

-0.66

 Cohn

-0.66

ĸļ

-0.65

 Hawth

-0.64

POSITIVE LOGITS

existing

1.40

empt

1.24

trial

1.23

requisites

1.22

release

1.21

requisite

1.15

jud

1.13

season

1.13

historic

1.10

existent

1.10

Activations Density 0.020%

prefixes related to placement or sequence

phrases related to preemptive actions or measures

No Comments

No Known Activations