INDEX

Explanations

statistical values and significance in research data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Efq

-0.65

Numerade

-0.59

 myſelf

-0.58

writeFieldEnd

-0.58

 Monfieur

-0.56

ManagedBean

-0.55

ároz

-0.54

 архивлан

-0.54

 Anſ

-0.53

האם

-0.53

POSITIVE LOGITS

 AssemblyCulture

0.88

 científico

0.53

ErrUnexpectedEOF

0.52

twimg

0.49

piel

0.49

 vuur

0.47

 noten

0.47

ListItemIcon

0.47

참고

0.47

 note

0.47

Activations Density 0.401%

statistical values and significance in research data

No Comments

No Known Activations