INDEX

Explanations

phrases indicating skepticism or criticism towards institutional practices and beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

-0.98

（

-0.67

 الحره

-0.67

.(

-0.63

</h4>

-0.61

.*")]

-0.57

（

-0.54

。（

-0.54

Hentet

-0.52

POSITIVE LOGITS

?),

1.65

?).

1.63

!),

1.60

!).

1.56

),”

1.44

).</

1.41

!)

1.39

?)

1.38

)”.

1.38

)".

1.33

Activations Density 1.044%

phrases indicating skepticism or criticism towards institutional practices and beliefs

No Comments

No Known Activations