INDEX

Explanations

phrases related to statements or claims made by writers

oai_token-act-pair · gpt-3.5-turbo

instances of the end of a section or a new entry in a list of descriptions

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

 organised

-0.64

 precon

-0.64

 UNESCO

-0.63

 organized

-0.62

 visitation

-0.60

 buckets

-0.60

ãĥ¼ãĥĨ

-0.58

 establishing

-0.58

 replicated

-0.58

 bases

-0.58

POSITIVE LOGITS

lightly

1.16

omew

1.09

aved

1.02

pecially

1.02

iblings

1.02

pite

1.01

ayers

1.01

ources

1.01

atisf

0.98

olo

0.97

Activations Density 0.034%

phrases related to statements or claims made by writers

instances of the end of a section or a new entry in a list of descriptions

No Comments

No Known Activations