INDEX

Explanations

references to various types of illness or health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

{{

-0.70

::$_

-0.60

 ujednoznacz

-0.59

']=='

-0.57

{{

-0.56

'@/

-0.55

 Архивная

-0.54

TestData

-0.53

 Delegates

-0.52

'{{

-0.50

POSITIVE LOGITS

[]:

0.93

 Gulf

0.89

Gulf

0.77

Xna

0.76

</u>

0.75

twimg

0.72

 gulf

0.72

хьтан

0.68

】

0.68

parsedMessage

0.67

Activations Density 0.058%

references to various types of illness or health conditions

No Comments

No Known Activations