INDEX

Explanations

terms related to complexity and moral ambiguity in storytelling or character dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.89

-0.88

-0.87

-0.86

is

-0.82

in

-0.75

-0.73

-0.71

are

-0.70

POSITIVE LOGITS

 betweenstory

1.45

Autoritní

1.31

 myſelf

1.25

 purpoſe

1.22

*/;

1.19

 propOrder

1.16

 Jefus

1.16

__":

1.16

 ſtate

1.16

}}]{

1.16

Activations Density 18.659%

terms related to complexity and moral ambiguity in storytelling or character dynamics

No Comments

No Known Activations