INDEX

Explanations

phrases related to selection bias in studies or surveys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

endphp

-0.66

 nakalista

-0.59

 informée

-0.56

onViewCreated

-0.55

 PeEnEo

-0.49

MessageTagHelper

-0.47

戬

-0.46

ſp

-0.46

providedIn

-0.46

ANTLR

-0.45

POSITIVE LOGITS

mbitos

0.35

 Impression

0.34

impression

0.33

 impression

0.33

sendTo

0.33

ViewImports

0.33

 quedarse

0.33

 bias

0.32

repr

0.32

blij

0.31

Activations Density 0.276%

phrases related to selection bias in studies or surveys

No Comments

No Known Activations