INDEX

Explanations

references to substitutes or alternatives 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 @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

InputBorder

-0.75

 kasarigan

-0.68

ViewFeatures

-0.62

featureID

-0.62

ClientSize

-0.59

HasForeignKey

-0.59

BorderFactory

-0.58

 pinulongan

-0.58

InteropServices

-0.57

MIDDLEWARE

-0.56

POSITIVE LOGITS

 alternative

2.99

 alternatives

2.81

alternative

2.68

 Alternative

2.62

Alternative

2.56

 Alternatives

2.46

alternatives

2.43

Alternatives

2.40

 alternativa

2.32

 ALTERNATIVE

2.32

Activations Density 0.523%

references to substitutes or alternatives in various contexts

No Comments

No Known Activations