INDEX

Explanations

phrases indicating causation or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

'{@

-0.67

 batalha

-0.67

 entgegen

-0.60

 escuchadas

-0.60

 casó

-0.60

 voraus

-0.58

 strå

-0.57

styleable

-0.57

 fluence

-0.57

 enfans

-0.55

POSITIVE LOGITS

 resulted

0.90

 caused

0.80

 resulting

0.80

ToAction

0.80

 increased

0.79

 eventual

0.78

导致

0.77

 causes

0.76

 causing

0.74

caused

0.72

Activations Density 0.347%

phrases indicating causation or results

No Comments

No Known Activations