INDEX

Explanations

specific tokens or code structures in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 beschäf

-0.49

ClientSize

-0.49

 Curiosity

-0.48

 fascination

-0.46

 Debe

-0.46

 penghargaan

-0.46

Especies

-0.45

 curiously

-0.45

บค

-0.45

Debe

-0.45

POSITIVE LOGITS

 betweenstory

0.70

0.67

 Organiser

0.62

 activist

0.61

 mobili

0.60

 mobilisation

0.60

EventLoop

0.60

 mobilization

0.60

 activists

0.59

 strateg

0.57

Activations Density 0.576%

specific tokens or code structures in the text

No Comments

No Known Activations