INDEX

Explanations

references to distributions and related financial terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

+#+

-0.85

 vostri

-0.74

 Bohr

-0.73

 oocytes

-0.73

Erg

-0.72

cinogen

-0.72

lek

-0.70

 Leroy

-0.69

لح

-0.69

Erg

-0.69

POSITIVE LOGITS

 distribution

1.85

 distribu

1.67

 distributing

1.63

 Distribution

1.62

 distribute

1.60

 distributions

1.59

 distributed

1.54

Distribution

1.54

distribution

1.53

 distributes

1.52

Activations Density 0.095%

references to distributions and related financial terms

No Comments

No Known Activations