INDEX

Explanations

references to safety features and product specifications

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

PerformLayout

-0.62

 <<<<<<<<<<<<<<

-0.61

RenderAtEndOf

-0.58

SOME

-0.57

 irgendwie

-0.55

 Obrador

-0.55

SourceChecksum

-0.55

Демографія

-0.54

 Stupid

-0.53

ècie

-0.53

POSITIVE LOGITS

 your

0.70

 effortlessly

0.64

 perfect

0.64

 effortless

0.64

 optimale

0.61

 optimal

0.61

 easily

0.61

PERFECT

0.61

 optimum

0.60

 precise

0.59

Activations Density 0.280%

references to safety features and product specifications

No Comments

No Known Activations