INDEX

Explanations

expressions indicating perceptions or observations about situations

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

dymyr

-0.48

 zdarma

-0.47

 chiesto

-0.47

 supuesto

-0.46

avedra

-0.46

 yelek

-0.45

 asla

-0.45

هرة

-0.45

 förr

-0.44

 cintura

-0.44

POSITIVE LOGITS

enumii

0.94

 CreateTagHelper

0.94

 ProtoMessage

0.91

 MainAxisSize

0.91

PerformLayout

0.89

 snippetHide

0.87

enumi

0.87

SharedDtor

0.86

DockStyle

0.82

 dAtA

0.82

Activations Density 0.282%

expressions indicating perceptions or observations about situations

No Comments

No Known Activations