INDEX

Explanations

combinations of words indicating options or choices

oai_token-act-pair · gpt-3.5-turbo

phrases indicating choices or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hens

-0.74

olics

-0.65

 GDDR

-0.64

ITED

-0.64

hak

-0.60

len

-0.60

Ced

-0.59

 Meng

-0.59

drawn

-0.58

liam

-0.57

POSITIVE LOGITS

 latter

1.49

 extremes

1.13

 possibilities

1.10

 genres

1.07

 factors

1.03

 categories

0.99

 modes

0.98

 scenarios

0.97

 options

0.95

 types

0.94

Activations Density 0.260%

combinations of words indicating options or choices

phrases indicating choices or options

No Comments

No Known Activations