INDEX

Explanations

references to people and their actions or perceptions

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

cée

-0.65

 kív

-0.52

umis

-0.52

θεί

-0.50

roli

-0.49

 kepem

-0.49

 autobiography

-0.49

igte

-0.48

 rodillas

-0.48

 leçons

-0.48

POSITIVE LOGITS

 people

1.28

ppl

1.12

people

1.07

 People

1.02

People

1.02

 ludzie

0.97

 PEOPLE

0.96

 folks

0.94

 Leute

0.87

 mensen

0.87

Activations Density 0.188%

references to people and their actions or perceptions

No Comments

No Known Activations