INDEX

Explanations

phrases that indicate obstacles or issues in a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

+:+

-0.64

 AssemblyProduct

-0.59

MethodImpl

-0.59

سطس

-0.59

 AttributeSet

-0.57

PutMapping

-0.54

Πηγές

-0.54

 SKIP

-0.53

таратура

-0.52

jewództ

-0.51

POSITIVE LOGITS

IsContent

0.59

 lack

0.58

 gevolg

0.54

 Infórmanos

0.54

 worse

0.53

PyErr

0.53

 root

0.52

 Lack

0.49

 poor

0.49

 Band

0.48

Activations Density 0.712%

phrases that indicate obstacles or issues in a discussion

No Comments

No Known Activations