INDEX

Explanations

references to interpersonal relationships and emotional experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

complexContent

-0.63

Hochspringen

-0.61

agami

-0.59

vatar

-0.59



-0.58

 continuant

-0.58

MLLoader

-0.58

Хьажоргаш

-0.57

 createSlice

-0.55

 NUKAT

-0.54

POSITIVE LOGITS

 whenever

0.84

 every

0.82

 Whenever

0.82

whenever

0.79

 frequently

0.78

 daily

0.78

Whenever

0.76

every

0.73

 everytime

0.72

 occasionally

0.71

Activations Density 0.492%

references to interpersonal relationships and emotional experiences

No Comments

No Known Activations