INDEX

Explanations

adjectives and phrases related to attributes or characteristics

oai_token-act-pair · gpt-3.5-turbo

key terms related to classifications and identity distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Â«

-0.82

 ï¿½

-0.80

 ãĢĮ

-0.77

 Â§Â§

-0.68

ãĢĮ

-0.66

 Berks

-0.66

 Administ

-0.59

''

-0.59

âĶĢ

-0.59

().

-0.59

POSITIVE LOGITS

1.49

"?

1.42

"!

1.40

",

1.38

"-

1.37

")

1.35

".

1.28

"—

1.27

";

1.25

").

1.25

Activations Density 0.307%

adjectives and phrases related to attributes or characteristics

key terms related to classifications and identity distinctions

No Comments

No Known Activations