INDEX

Explanations

concepts and discussions related to ideological critiques and legal judgments

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

 يتيمه

-0.70

הערות

-0.59

 חיצוניים

-0.58

êts

-0.55

OOT

-0.54

ötet

-0.54

 useHistory

-0.53

didReceive

-0.53

 Halen

-0.53

 habis

-0.52

POSITIVE LOGITS

 bahwa

0.86

 ότι

0.85

ว่า

0.76

 kwamba

0.72

 that

0.69

 πως

0.68

 rằng

0.68

">//

0.64

 bahawa

0.62

 مب

0.62

Activations Density 0.502%

concepts and discussions related to ideological critiques and legal judgments

No Comments

No Known Activations