INDEX

Explanations

terms related to coding and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 möjligt

-0.74

 Zjednoc

-0.65

 douceur

-0.64

cils

-0.63

 CreateTagHelper

-0.63

 ActivatedRoute

-0.62

odiment

-0.62

مصادر

-0.61

prepareStatement

-0.61

 invid

-0.60

POSITIVE LOGITS

 Gund

1.07

Bronnen

0.99

0.97

GS

0.93

0.88

GSC

0.88

 kasarigan

0.87

GV

0.84

gs

0.84

GES

0.83

Activations Density 1.120%

terms related to coding and data structures

No Comments

No Known Activations