INDEX

Explanations

references to various presidents and presidential terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oog

-0.72

 Roskov

-0.72

 Borgo

-0.71

 Turin

-0.71

ske

-0.69

jerg

-0.67

ỡng

-0.67

items

-0.65

LK

-0.64

'</

-0.64

POSITIVE LOGITS

 Presidents

1.30

 presidents

1.21

Presidents

1.16

 President

1.12

 president

1.02

 PRESIDENT

1.00

 presidential

0.99

Portail

0.94

 Presidential

0.93

PerformLayout

0.91

Activations Density 0.072%

references to various presidents and presidential terms

No Comments

No Known Activations