INDEX

Explanations

phrases or words related to specific terms or names

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols used in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

``

-1.22

Âł

-0.93

````

-0.88

`,

-0.87

``

-0.86

`.

-0.84

-0.82

ÂłÂłÂł

-0.80

-0.78

ÂłÂł

-0.74

POSITIVE LOGITS

—

3.19

 âĢķ

2.17

 ÂŃ

1.84

—

1.77

—"

1.51

--

1.49

 âĢ¦

1.47

.—

1.38

–

1.36

Enlarge

1.29

Activations Density 0.096%

phrases or words related to specific terms or names

special characters or symbols used in the text

No Comments

No Known Activations