INDEX

Explanations

questions and statements related to inquiry or affirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 ―――――

-0.75

principalColumn

-0.72

+#+#

-0.72

 Whigs

-0.72

 themſelves

-0.70

Efq

-0.70

 myſelf

-0.70

 سكانية

-0.70

 Houſe

-0.69

 itſelf

-0.69

POSITIVE LOGITS

 anyone

1.08

 anybody

0.97

 everyone

0.85

 everybody

0.79

anyone

0.79

Anybody

0.77

 this

0.74

 Anybody

0.70

Anyone

0.70

nt

0.68

Activations Density 0.116%

questions and statements related to inquiry or affirmation

No Comments

No Known Activations