INDEX

Explanations

references to selection processes and choices made by users in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ExtendWith

-0.69

MLLoader

-0.68

ViewImports

-0.65

RunWith

-0.60

ViewFeatures

-0.60

titleMargin

-0.58

tagHelperRunner

-0.58

WithIOException

-0.57

RTEE

-0.56

IonicModule

-0.56

POSITIVE LOGITS

 choice

3.03

 selection

3.02

 choose

2.91

 chosen

2.90

 selected

2.88

 choosing

2.84

 selecting

2.79

 select

2.67

 chose

2.66

 chooses

2.66

Activations Density 1.006%

references to selection processes and choices made by users in various contexts

No Comments

No Known Activations