INDEX

Explanations

terms related to "range" and "ranging" 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

MENAFN

-0.81

AsUp

-0.73

EDEFAULT

-0.71

\{\\

-0.70

олові

-0.69

 voyez

-0.67

 autorytatywna

-0.63

BeginContext

-0.63

QMetaType

-0.61

 Bioaccumulative

-0.59

POSITIVE LOGITS

 range

4.60

 Range

4.38

Range

4.29

range

4.28

 RANGE

4.09

 ranges

3.81

RANGE

3.74

 Ranges

3.32

ranges

3.23

Ranges

3.00

Activations Density 0.071%

terms related to "range" and "ranging" in various contexts

No Comments

No Known Activations