INDEX

Explanations

references to separate entities or comparisons within analytical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

MockMvc

-0.65

 '*':

-0.60

++

-0.59

Décès

-0.59

міністра

-0.57

 similit

-0.57

Abitanti

-0.56

ésultat

-0.55

pakatan

-0.55

Temporada

-0.54

POSITIVE LOGITS

 separately

1.79

 individually

1.78

 individual

1.74

 separate

1.68

Individual

1.57

单独

1.57

individual

1.55

 Individual

1.55

 Separate

1.50

separate

1.45

Activations Density 0.878%

references to separate entities or comparisons within analytical contexts

No Comments

No Known Activations