INDEX

Explanations

terms related to contests and winning incentives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

("]");

-0.53

 Weyl

-0.52

)";

-0.52

diert

-0.51

hoc

-0.51

 cref

-0.47

CloseOperation

-0.47

ganu

-0.46

"';

-0.45

 ↓,

-0.45

POSITIVE LOGITS

 winners

1.56

 prizes

1.56

 prize

1.54

 winner

1.46

 raffle

1.46

 Prizes

1.43

 contest

1.39

 winning

1.35

 Winners

1.34

 Prize

1.34

Activations Density 0.097%

terms related to contests and winning incentives

No Comments

No Known Activations