INDEX

Explanations

assertions of wrongdoing or failures in actions, particularly in contexts that involve approvals or 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

setLayoutManager

-0.72

createCanvas

-0.58

ciss

-0.56

phard

-0.53

thenReturn

-0.53

Биография

-0.52

 userDao

-0.51

 nærm

-0.49

nout

-0.49

iegler

-0.49

POSITIVE LOGITS

 וגם

0.85

 /\.(

0.74

MLLoader

0.69

 utafitiHapana

0.67

 también

0.66

también

0.63

 ProtoMessage

0.63

 tambien

0.63

кож

0.63

Diweddarwch

0.63

Activations Density 0.496%

assertions of wrongdoing or failures in actions, particularly in contexts that involve approvals or evaluations

No Comments

No Known Activations