INDEX

Explanations

the word "Mor" followed by another part of a word

oai_token-act-pair · gpt-3.5-turbo

references to a specific individual or entity named "Mor."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Reboot

-0.63

 false

-0.62

-0.61

 packaging

-0.60

JECT

-0.59

bay

-0.59

 dism

-0.59

 heartbeat

-0.56

 depreciation

-0.56

 dormant

-0.55

POSITIVE LOGITS

pheus

1.48

neau

1.31

imoto

1.28

atorium

1.14

bid

1.11

rill

1.11

rigan

1.10

phe

1.09

rison

1.09

rell

1.00

Activations Density 0.029%

the word "Mor" followed by another part of a word

references to a specific individual or entity named "Mor."

No Comments

No Known Activations