INDEX

Explanations

terms related to stability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

-0.69

↵

-0.69

cu

-0.66

Pod

-0.65

pod

-0.64

<eos>

-0.63

ond

-0.63

“

-0.62

”

-0.62

POSITIVE LOGITS

 Stable

1.76

Stable

1.58

 stabilisation

1.55

 myſelf

1.53

 Stabili

1.51

 itſelf

1.51

 Stability

1.50

 stabilization

1.49

 iſt

1.49

unstable

1.48

Activations Density 0.126%

terms related to stability

No Comments

No Known Activations