INDEX

Explanations

terms related to biological processes and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 encouragement

-0.65

 assistance

-0.64

 intervention

-0.60

 intervened

-0.60

 disruption

-0.59

 dissatisfaction

-0.59

 responsiveness

-0.58

 frustration

-0.57

sibility

-0.57

 inconvenience

-0.57

POSITIVE LOGITS

Millions

0.67

millions

0.65

 thousands

0.64

massive

0.64

 Millions

0.63

 massive

0.62

 HUGE

0.61

thousands

0.61

 billions

0.61

 millions

0.60

Activations Density 2.114%

terms related to biological processes and interactions

No Comments

No Known Activations