INDEX

Explanations

phrases indicating insufficient evidence or inadequate explanation

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

UnusedPrivate

-0.51

inaldi

-0.51

 automatiques

-0.44

imals

-0.42

PhysRev

-0.42

etu

-0.42

ugno

-0.41

carpus

-0.41

 generaciones

-0.40

earlier

-0.40

POSITIVE LOGITS

 nakalista

0.67

 CreateTagHelper

0.63

__))

0.62

matchCondition

0.61

 للاسماء

0.61

))^

0.59

]');

0.58

Personensuche

0.57

хьтан

0.56

 vấn

0.52

Activations Density 0.470%

phrases indicating insufficient evidence or inadequate explanation

No Comments

No Known Activations