INDEX

Explanations

references to philosophy and ethical discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

כז

-0.65

 Martinez

-0.64

Occurrences

-0.61

佼

-0.60

ContentAlignment

-0.60

microb

-0.57

 CENT

-0.57

phen

-0.56

יי

-0.56

POSITIVE LOGITS

Philosophy

1.23

 Philosophy

1.22

 philosopher

1.22

 philosophers

1.20

 philosoph

1.20

 philosophical

1.16

 filosof

1.16

 philosophy

1.16

 Philosopher

1.14

 philosophies

1.12

Activations Density 0.105%

references to philosophy and ethical discussions

No Comments

No Known Activations