INDEX

Explanations

references to animals in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ADATA

-0.43

rics

-0.40

mene

-0.38

liv

-0.38

roms

-0.37

mener

-0.37

渣

-0.37

stead

-0.37

UTERS

-0.37

ans

-0.36

POSITIVE LOGITS

 animal

2.06

animal

1.85

 ANIMAL

1.85

 animals

1.82

Animal

1.78

 bird

1.78

 Animal

1.77

ANIMAL

1.73

 rabbit

1.69

Animals

1.67

Activations Density 2.381%

references to animals in various contexts

No Comments

No Known Activations