INDEX

Explanations

terms related to mental processes and emotional states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

mybatisplus

-0.64

Życiorys

-0.56

 metrów

-0.51

 démar

-0.49

mål

-0.48

hdashline

-0.48

ERO

-0.48

 AppCompatTheme

-0.47

 marcato

-0.47

ietf

-0.47

POSITIVE LOGITS

bog

0.64

Попис

0.63

Personensuche

0.63

 wandering

0.63

palace

0.62

 wanders

0.61

AccessorTable

0.60

 wander

0.60

 wandered

0.59

Personendaten

0.58

Activations Density 0.173%

terms related to mental processes and emotional states

No Comments

No Known Activations