INDEX

Explanations

numerical values or quantities related to data or analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 nahilalakip

-0.69

CodeAttribute

-0.63

 CYTHON

-0.60

WriteAttribute

-0.59

 surla

-0.58

SpringBootTest

-0.58

 nonatomic

-0.57

\{\\

-0.57

 StringTokenizer

-0.56

cokinetics

-0.56

POSITIVE LOGITS

ondissement

0.84

th

0.77

Manbalar

0.71

Ведь

0.66

thme

0.63

 useHistory

0.63

 Dage

0.62

thand

0.62

 Dalai

0.62

esimo

0.61

Activations Density 0.332%

numerical values or quantities related to data or analysis

No Comments

No Known Activations