INDEX

Explanations

instances of actions or states related to knowledge and responsibility

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AccessorTable

-0.77

sizeCache

-0.75

antMatchers

-0.70

getMenuInflater

-0.70

CloseOperation

-0.68

 snippetHide

-0.66

 nakalista

-0.64

Erreferentziak

-0.63

archiviato

-0.61

indd

-0.61

POSITIVE LOGITS

ırl

0.50

arusian

0.44

PASSED

0.43

chaik

0.42

кість

0.41

ք

0.41

vodu

0.40

 oliva

0.40

clerview

0.40

Carrière

0.40

Activations Density 0.325%

instances of actions or states related to knowledge and responsibility

No Comments

No Known Activations