INDEX

Explanations

the word "Fu" with various levels of activation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Fu," likely related to a name or entity

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

worthiness

-0.79

 Emin

-0.76

 Remastered

-0.70

theless

-0.68

 Apostles

-0.66

sheets

-0.64

pheus

-0.64

*/(

-0.64

ãģĨ

-0.63

 Pioneer

-0.61

POSITIVE LOGITS

selage

1.63

lda

1.25

jin

1.09

ÃŁ

1.05

qua

1.02

pport

1.00

ze

0.99

els

0.99

zed

0.96

cci

0.95

Activations Density 0.058%

the word "Fu" with various levels of activation

occurrences of the word "Fu," likely related to a name or entity

No Comments

No Known Activations