INDEX

Explanations

references to studies and insights from psychology and neuroscience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Datuak

-0.77

 оригіналу

-0.70

ViewFeatures

-0.67

setVerticalGroup

-0.63

ConverterFactory

-0.57

InjectAttribute

-0.56

 resourceCulture

-0.52

 springfox

-0.51

 खरीदा

-0.51

SerializedName

-0.50

POSITIVE LOGITS

 tell

2.90

 Tell

2.57

 told

2.56

 telling

2.55

Tell

2.54

 tells

2.52

 TELL

2.50

tell

2.34

told

2.26

 Telling

2.25

Activations Density 0.389%

references to studies and insights from psychology and neuroscience

No Comments

No Known Activations