INDEX

Explanations

phrases that describe outcomes or products resulting from processes

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

舉

-0.48

 welche

-0.46

abbaye

-0.45

举

-0.45

Grpc

-0.44

seamnă

-0.44

Atsauces

-0.42

routeProvider

-0.42

 begren

-0.42

radas

-0.41

POSITIVE LOGITS

 outcome

0.94

 resultado

0.94

 resultant

0.92

DockStyle

0.92

成品

0.90

 RESULT

0.88

 résult

0.86

 resulting

0.85

 result

0.85

 résultat

0.84

Activations Density 0.601%

phrases that describe outcomes or products resulting from processes

No Comments

No Known Activations