INDEX

Explanations

configuration-related terms or keywords

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 AssemblyTitle

-1.02

+#+#

-0.80

 mergeFrom

-0.76

SourceChecksum

-0.74

ChildScrollView

-0.73

icoot

-0.71

 transfieras

-0.71

 Италијани

-0.69

)";

-0.69

DNEY

-0.69

POSITIVE LOGITS

 conf

1.35

conf

1.34

Conf

1.27

 Conf

1.14

 CONF

0.87

CONF

0.86

 confessions

0.75

 confess

0.71

 comfort

0.70

 confession

0.67

Activations Density 0.043%

configuration-related terms or keywords

No Comments

No Known Activations