INDEX

Explanations

references to a television show

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

bereits

-0.67

 genomen

-0.65

ätzlich

-0.65

延伸閱讀

-0.65

 liggen

-0.64

 miatt

-0.64

teile

-0.64

 ambientales

-0.64

 necessari

-0.64

 Brito

-0.63

POSITIVE LOGITS

 SHOW

1.93

SHOW

1.90

 show

1.85

 Show

1.84

Show

1.81

show

1.81

 Shows

1.61

shows

1.60

 shows

1.59

 shew

1.47

Activations Density 0.048%

references to a television show

No Comments

No Known Activations