INDEX

Explanations

instances where comparisons are made between different subjects or methods

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

 Rosenberg

-0.71

Bism

-0.64

lidene

-0.63

entgen

-0.63

jectories

-0.63

Man

-0.59

ubourg

-0.59

tserrat

-0.58

 irgende

-0.58

 episódios

-0.57

POSITIVE LOGITS

 comparison

2.27

 comparisons

2.21

 Comparisons

2.12

 Comparison

2.03

 comparing

2.02

Comparison

1.90

 compares

1.89

 Compare

1.87

 Comparing

1.87

comparison

1.86

Activations Density 0.119%

instances where comparisons are made between different subjects or methods

No Comments

No Known Activations