INDEX

Explanations

occurrences of the word "apache"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

)|\

-0.61

sohn

-0.60

={{

-0.58

{}\

-0.57

cellaneous

-0.56

DetailView

-0.54

MetaData

-0.53

tabular

-0.53

liato

-0.52

>>>

-0.52

POSITIVE LOGITS

apache

1.06

 propOrder

0.99

stdc

0.88

 kernel

0.88

kernel

0.88

principalColumn

0.86

 slope

0.78

 Kernel

0.77

 صوتيه

0.77

 slopes

0.77

Activations Density 0.054%

occurrences of the word "apache"

No Comments

No Known Activations