INDEX

Explanations

terms related to research methodologies and evaluations

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

misu

-0.46

 orar

-0.46

 permanently

-0.43

hobia

-0.42

 ejus

-0.42

 excavated

-0.42

 migrating

-0.41

 supervising

-0.41

 circulating

-0.40

buttonShape

-0.40

POSITIVE LOGITS

enumi

0.69

adpleegd

0.67

 AssemblyCulture

0.66

 Closer

0.65

 AssemblyProduct

0.63

Closer

0.63



0.63

 CGPoint

0.62

########.

0.62

greif

0.61

Activations Density 1.416%

terms related to research methodologies and evaluations

No Comments

No Known Activations