INDEX

Explanations

negative descriptors related to intelligence and social status

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

 démocr

-0.57

GraphicsUnit

-0.56

 médicas

-0.55

guien

-0.54

 kennis

-0.53

zda

-0.52

 ſever

-0.52

 résister

-0.51

 fevere

-0.51

 händ

-0.51

POSITIVE LOGITS

 scum

0.99

 loser

0.92

 idiot

0.87

 slut

0.86

 bitch

0.86

 losers

0.85

 coward

0.84

 asshole

0.83

 whore

0.83

 bastard

0.82

Activations Density 0.381%

negative descriptors related to intelligence and social status

No Comments

No Known Activations