INDEX

Explanations

elements related to emotional responses in testimony or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

CppMethod

-0.57

 الحره

-0.56

.}~\

-0.52

]--;

-0.51

 beginnetje

-0.50

 يتيمه

-0.50

)++;

-0.49

aarrggbb

-0.48

OGND

-0.48

msgTypes

-0.48

POSITIVE LOGITS

[toxicity=0]

0.51

0.42

Deleted

0.39

0.38

Copia

0.38

0.37

Ad

0.37

Activations Density 0.235%

elements related to emotional responses in testimony or narratives

No Comments

No Known Activations