INDEX

Explanations

specific terms referring to essential elements or details within a context

oai_token-act-pair · gpt-3.5-turbo

recurring phrases emphasizing the concept of "that"

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

ãĤ´ãĥ³

-0.98

ãĤ´

-0.84

hig

-0.83

SEE

-0.66

 Released

-0.65

Synopsis

-0.64

ãģ®é

-0.64

ãĥį

-0.63

imen

-0.63

FN

-0.62

POSITIVE LOGITS

 everybody

1.39

 somebody

1.38

we

1.26

1.20

 anybody

1.20

 they

1.05

['

1.04

you

1.03

 people

0.97

 maybe

0.94

Activations Density 0.339%

specific terms referring to essential elements or details within a context

recurring phrases emphasizing the concept of "that"

No Comments

No Known Activations