INDEX

Explanations

specific geographical locations and associated names or terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 themſelves

-0.86

 doubtnut

-0.74

 Jefus

-0.73

 itſelf

-0.72

 adventurers

-0.70

 skimming

-0.70

رشف

-0.68

WriteTagHelper

-0.68

twimg

-0.67

 jati

-0.67

POSITIVE LOGITS

Bats

0.68

endphp

0.67

erdin

0.65

Mas

0.63

addPreferredGap

0.61

MAS

0.60

Slu

0.59

 Bateman

0.58

 Mason

0.58

Bru

0.57

Activations Density 1.170%

specific geographical locations and associated names or terms

No Comments

No Known Activations