INDEX

Explanations

references and citations related to external sources and documentation

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

muir

-0.61

ggars

-0.61

 bill

-0.54

Detalhes

-0.53

rovna

-0.51

 bills

-0.51

oredCriteria

-0.50

biotics

-0.49

ughter

-0.48

Giới

-0.47

POSITIVE LOGITS

hline

3.30

cline

1.30

toprule

1.00

 <<<<<<<<<<<<<<

0.90

midrule

0.86

hdashline

0.85

 autorytatywna

0.81

\{\\

0.80

bottomrule

0.68

PerformLayout

0.68

Activations Density 0.031%

references and citations related to external sources and documentation

No Comments

No Known Activations