INDEX

Explanations

instances of completed actions or tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ThroughAttribute

-0.62

SerializedSize

-0.61

XmlAccessType

-0.60

 كومونز

-0.59

highlight

-0.58

Highlighted

-0.56

Eigenschaften

-0.56

stateProvider

-0.56

くださいね

-0.56

tersebut

-0.55

POSITIVE LOGITS

 doing

2.21

 done

2.17

Doing

2.15

 Doing

2.14

doing

1.93

 Done

1.93

Done

1.81

 DOING

1.79

 DONE

1.73

done

1.72

Activations Density 0.150%

instances of completed actions or tasks

No Comments

No Known Activations