INDEX

Explanations

terms related to eligibility and qualifications 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

verwijspagina

-1.08

 TimeUnit

-1.05

 ―――――

-1.04

 Theſe

-1.03

 itſelf

-0.99

Efq

-0.98

 Cæsar

-0.97

 pleaſure

-0.97

 whoſe

-0.95

 Majefty

-0.95

POSITIVE LOGITS

ç

0.64

0.59

<eos>

0.58

 Fast

0.56

0.54

су

0.54

0.53

0.52

Activations Density 0.095%

terms related to eligibility and qualifications in various contexts

No Comments

No Known Activations