INDEX

Explanations

strings related to legal or criminal activities

oai_token-act-pair · gpt-3.5-turbo

sentence-ending punctuation marks

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tremend

-1.11

 disturb

-0.82

 carbohyd

-0.81

 challeng

-0.80

 undermin

-0.79

 abundantly

-0.79

 desper

-0.78

 defin

-0.76

 unstoppable

-0.74

 millenn

-0.74

POSITIVE LOGITS

 Officials

1.41

 However

1.35

Its

1.32

 Previously

1.30

 Earlier

1.28

 According

1.24

 They

1.23

 Asked

1.23

 Later

1.23

But

1.23

Activations Density 0.402%

strings related to legal or criminal activities

sentence-ending punctuation marks

No Comments

No Known Activations