INDEX

Explanations

questions related to troubleshooting or seeking information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

usercontent

-0.50

setopt

-0.41

 test

-0.41

DebuggerStep

-0.40

łoż

-0.39

%>%

-0.39

deelte

-0.38

 unknownFields

-0.38

شیر

-0.38

pkg

-0.37

POSITIVE LOGITS

 resourceCulture

0.85

 betweenstory

0.80

ivably

0.77

 تضيفلها

0.75

WebElementEntity

0.75

 urgently

0.74

oredCriteria

0.73

Ideally

0.72

 Preferably

0.72

 Ideally

0.69

Activations Density 0.451%

questions related to troubleshooting or seeking information

No Comments

No Known Activations