INDEX

Explanations

terms related to acceptance or consent in various contexts

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

virons

-0.69

 Иль

-0.64

highly

-0.63

üglich

-0.62

 avrebbero

-0.62

mingen

-0.62

 devons

-0.61

 Polk

-0.61

 Barker

-0.61

Korn

-0.61

POSITIVE LOGITS

 accept

2.19

 Accept

2.11

 accepts

2.05

 acceptance

2.04

 ACCEPT

1.98

 accepted

1.97

 Accepting

1.96

 accepting

1.95

 Acceptance

1.91

accept

1.89

Activations Density 0.082%

terms related to acceptance or consent in various contexts

No Comments

No Known Activations