INDEX

Explanations

words related to data analysis and decision-making

oai_token-act-pair · gpt-3.5-turbo

references to casualties or impacts from events

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

''

-1.82

 âĢİ

-1.72

``

-1.56

''

-1.46

---

-1.34

``

-1.24

,...

-1.23

}}}

-1.22

---

-1.17

Advertisement

-1.14

POSITIVE LOGITS

–

2.38

.–

1.28

 ðŁĻĤ

1.25

–

1.23

âĢ³

1.09

 Isis

1.09

 Nasa

1.06

 âĢ¦"

1.05

Facebook

1.00

 âĢ¦

0.98

Activations Density 0.999%

words related to data analysis and decision-making

references to casualties or impacts from events

No Comments

No Known Activations