INDEX

Explanations

terms related to comparisons and mathematical expressions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

findpost

-0.86

eabouts

-0.77

/*

-0.76

DotNetBar

-0.73

guous

-0.69

 Anastasia

-0.69

 Newsroom

-0.68

 Herrick

-0.66

luf

-0.65

 Bioaccumulative

-0.65

POSITIVE LOGITS

 Leicestershire

1.15

 Leighton

1.12

 Leona

1.11

LE

1.08

 Leandro

1.04

le

1.02

LE

0.99

 Leal

0.99

 Leung

0.98

 Leto

0.98

Activations Density 0.281%

terms related to comparisons and mathematical expressions

No Comments

No Known Activations