INDEX

Explanations

phrases indicating opinions or assessments about judicial matters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

™.

-0.50

«

-0.49

))).

-0.46

®.

-0.45

.\\

-0.45

「

-0.44

}).

-0.44

:).

-0.43

“

-0.43

}}}

-0.43

POSITIVE LOGITS

1.23

[$

0.79

[_

0.75

[_

0.73

[]"

0.69

,"

0.68

0.60

」（

0.60

Activations Density 0.719%

phrases indicating opinions or assessments about judicial matters

No Comments

No Known Activations