INDEX

Explanations

references to folklore and legends, particularly those with historical or mythical aspects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

PhysRevD

-0.56

 خارجية

-0.54

ScopeManager

-0.52

rister

-0.52

发表于

-0.51

Lähteet

-0.50

ContentAsync

-0.50

TagMode

-0.50

ViewFeatures

-0.49

$__

-0.49

POSITIVE LOGITS

 legend

1.85

 myth

1.80

 legends

1.75

 myths

1.74

 folklore

1.72

 mythology

1.57

 Legend

1.46

legend

1.43

Legend

1.42

myth

1.37

Activations Density 0.267%

references to folklore and legends, particularly those with historical or mythical aspects

No Comments

No Known Activations