INDEX

Explanations

the word "Fu" at different levels of activation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Fu."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-0.85

sburgh

-0.75

 Remastered

-0.72

 Emin

-0.72

 Turing

-0.70

theless

-0.69

lihood

-0.68

èĢħ

-0.67

-0.66

 Orbit

-0.65

POSITIVE LOGITS

selage

1.62

lda

1.18

jin

1.10

pport

0.99

isine

0.98

ueless

0.95

emen

0.95

cci

0.95

els

0.94

ze

0.93

Activations Density 0.017%

the word "Fu" at different levels of activation

occurrences of the term "Fu."

No Comments

No Known Activations