INDEX

Explanations

phrases that indicate feedback and audience reaction to experiences or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 kasarigan

-0.63

Története

-0.59

 viewDidLoad

-0.54

LLocation

-0.54

RenderAtEndOf

-0.53

 timeval

-0.52

 HasFactory

-0.52

 asunder

-0.51

 متعلقه

-0.51

piecze

-0.51

POSITIVE LOGITS

 response

1.65

 responses

1.56

 feedback

1.56

 reacties

1.45

 reactions

1.44

 reaction

1.42

 reception

1.33

response

1.33

 Responses

1.28

feedback

1.26

Activations Density 0.287%

phrases that indicate feedback and audience reaction to experiences or products

No Comments

No Known Activations