INDEX

Explanations

references to the sufficiency or adequacy of information or facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Kar

-0.71

="{{

-0.70

Pyx

-0.70

SerializedSize

-0.69

Kay

-0.67

rs

-0.66

Enders

-0.64

 JADX

-0.64

Ser

-0.63

 Wirt

-0.61

POSITIVE LOGITS

 ENOUGH

1.47

 enough

1.47

enough

1.44

 Enough

1.44

Enough

1.32

 suffic

1.17

 fufficient

1.11

ufficient

1.07

 Sufficient

1.07

Sufficient

1.06

Activations Density 0.096%

references to the sufficiency or adequacy of information or facts

No Comments

No Known Activations