INDEX

Explanations

terms related to evidence and its effects in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ThroughAttribute

-1.07

Efq

-0.94

 myſelf

-0.85

 itſelf

-0.80

UnsafeEnabled

-0.79

 himſelf

-0.79

 plufieurs

-0.78

principalTable

-0.78

 onAnimation

-0.78

 obfer

-0.78

POSITIVE LOGITS

ro

0.47

gra

0.46

ad

0.46

til

0.46

con

0.45

=>

0.45

in

0.44

em

0.44

del

0.43

Activations Density 1.539%

terms related to evidence and its effects in a scientific context

No Comments

No Known Activations