INDEX

Explanations

references to the name "Jordan" across 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 @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 للمعارف

-0.94

 CreateTagHelper

-0.86

 وتسجيلات

-0.85

RTEX

-0.83

 defaultstate

-0.82

 Priory

-0.75

aarrggbb

-0.72

 Hopf

-0.72

SharedCtor

-0.71

rungsseite

-0.71

POSITIVE LOGITS

Edited

0.74

 Jordan

0.74

trecht

0.72

Jordan

0.69

Wol

0.69

 bact

0.69

 compren

0.65

 jordan

0.65

 Salz

0.65

 Jord

0.64

Activations Density 1.659%

references to the name "Jordan" across various contexts

No Comments

No Known Activations