INDEX

Explanations

phrases involving the action of "putting."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Administrativna

-0.82

WriteTagHelper

-0.82

UnusedPrivate

-0.75

ContentLoaded

-0.74

InitVars

-0.72

 schuldig

-0.69

MigrationBuilder

-0.69

الحياه

-0.68

bootstrapcdn

-0.68

Erreferentziak

-0.68

POSITIVE LOGITS

put

1.36

Put

1.31

Put

1.25

Putting

1.20

put

1.17

 puts

1.13

PUT

1.12

 Putting

1.12

 putting

1.09

putting

1.08

Activations Density 0.078%

phrases involving the action of "putting."

No Comments

No Known Activations